JP4149179B2 - Endotracheal examination diagnosis support device, intratracheal inspection diagnosis support method, and storage medium storing intratracheal inspection diagnosis support program - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention is based on video data obtained by photographing the inner wall surface of a large and small caliber pipe, such as water / sewage pipes, tunnels for transportation such as railways, roadways, and sidewalks, cable buried pipes, etc. PC images can be displayed as still images, created in the longitudinal direction, or displayed as movies or still images. The present invention relates to a tube inspection / diagnosis support apparatus, a tube inspection / diagnosis support method, and a storage medium storing a tube inspection / diagnosis support program.
[0002]
[Prior art]
Conventionally, the inspection of the wall surface of the pipe has been mainly performed by drawing a deformation by visual observation while a person walks around in a dark and long pipe and creating a development view based on the drawing. In this method, the object to be inspected is a large structure, and there are many long pipe rods. Therefore, not only a lot of manpower and time are required, but it is difficult to accurately capture all deformations. In addition, inspection of the wall surface of the pipe wall, which has a small diameter for water supply and sewerage and cannot be entered by humans, is carried out by moving a video camera or the like, but it cannot be accurately inspected.
[0003]
An apparatus for processing a tube inner surface image for continuous inspection is already known (Japanese Patent Application Laid-Open No. 2000-331168, hereinafter referred to as “Publication”). As shown in FIG. 11, a so-called fish-eye lens 61 having an angle of view (vertical angle of view) of 180 degrees or more is used as the omnidirectional sensor (or panoramic sensor) of the camera to shoot. is there. The fish-eye lens 61 is a double-sided convex lens as a whole, but has a shape cut so that the central portion of one surface (the right side surface in FIG. 11A) is concave and the central portion of the other surface is flat. None, the concave cut portion on one side is the reflecting surface 65 of the convex mirror viewed from the inside of the fisheye lens 61, and the flat cut portion on the other side is the transmitting surface 66 from which the light is refracted and emitted. None, the outer peripheral surface on the reflecting surface 65 side of the convex mirror constitutes an incident surface 68 on which light is incident, and the outer peripheral surface on the transmitting surface 66 side constitutes a reflecting surface 67 on which light is reflected.
It is assumed that the fisheye lens 61 configured in this way is configured such that the maximum shooting angle αmax is 115 degrees and the minimum shooting angle αmin is 45 degrees with respect to the optical axis S of the video camera 35 in the visible range.
[0004]
The image data when the center line S of the fisheye lens 61 and the center line of the tub 10 are set to coincide with each other will be described.
The image data (x, y) of the shooting angle α within the visible range of the wall surface 11 is a circle whose center is the center of the fisheye lens 61 and whose radius is proportional to the shooting angle α, as shown in FIG.
[0005]
As shown in FIG. 12, the correspondence between the position of the wall surface 11 of the tube rod 10 and the coordinate data of the developed view when the video camera 35 is set in the center of the tube rod 10 toward the center line S will be described. To do.
As shown in FIG. 13A, the image of one frame when the maximum shooting angle αmax = 90 degrees and the minimum shooting angle αmin = 45 degrees projected by the video camera 35 is a wall image 75 having a donut shape on the outer periphery. The central portion (shaded portion) becomes a non-projection portion 73, and among these, the wall surface image 75 is converted into a coordinate point (m, n) on the development view corresponding to the coordinate point (x, y) on the actual image data by the expansion processing. When a development view is created from the obtained coordinate data, the development view is developed in the longitudinal direction of the tube rod 10 as shown in FIG.
12 and 13 (a) (b), if the mesh or lattice pattern in the optical axis direction and the circumferential direction is a typical crack, 14a in FIG. 14b in FIG. 13 (a) shows a crack in the image projected by the video camera 35, and 14c in FIG. 13 (b) shows a crack in the developed view.
[0006]
The fisheye lens 61 is an area where the substantially central portion is hardly used as a reflecting mirror. Therefore, as shown in FIG. 14A, the central portion of the reflection surface 65 is removed to form a transmission portion 70. Then, a linear video signal e from the front of the tube 10 can be taken in, and the video signal e is originally a portion that was the non-projection part 73 in the central portion as shown in FIG. Can be displayed as an image f. Therefore, it can be used as the forward monitoring image 74 of the tube 10.
[0007]
It is desirable that the non-projection unit 73 projects the monitoring image 74 as much as possible on the whole. For this purpose, a zoom lens 71 is interposed between the relay lens 62 and the image sensor 63. Then, in FIG. 14A, the video signal e is enlarged and projected like the video signal F (FIG. 14C).
When the area of the video signal e for forward monitoring is too narrow, the wide-angle lens 72 is interposed in front of the fisheye lens 61, but the video signal e is not enlarged as shown in FIG. The area is expanded.
[0008]
Next, an image data processing portion of the tube rod inner surface image processing apparatus described in the above-mentioned publication using the fisheye lens 61 as described above will be described with reference to FIG.
This apparatus is composed of three parts: a video data input device 36, a development view processing device 37, and a development view output device 39.
[0009]
The video data input device 36 is composed of a video deck 40 and a video capture board 41, and takes in image data indicating the condition of the wall surface 11 of the tube 10.
The developed view processing device 37 recognizes characters from the image data storage unit 42 for storing the image data from the video data input device 36, and the image data in the image data storage unit 42, and converts the character information to the developed view. An omnidirectional sensor 61 (two-leaf hyperboloid mirror, fisheye lens, etc.) is used for the character recognition processing unit 56 to output and the video camera 35 of the video data input device 36 for the stored data, the video camera 35 is tilted, An omnidirectional sensor development correction processing unit 44 that corrects distortion caused by an optical axis misalignment or the like and creates a development drawing for each frame from the stored corrected data. A development data storage unit 45 to store, a data matching unit 46 for performing data matching for distortion adjustment between image data for each frame, A development view is created by adding character information from the character recognition processing unit 56 and character information from a damage determination unit 51 (to be described later) and combining image data for a plurality of frames after distortion adjustment from the data matching unit 46. And a developed view storage unit 48 for storing the developed view created by the developed view creating unit 47.
[0010]
The development drawing creation order by the processing device for tube inner surface images described in the above publication will be described.
The image signal of the wall surface 11 of the tube 10 is input to the video deck 40 of the video data input device 36 for each frame.
The image data is stored in the image data storage unit 42 of the developed view processing device 37.
[0011]
Based on the image data in the image data storage unit 42, the character recognition processing unit 56 performs a process for recognizing character information on the screen such as the moving distance and the rotation angle of the video camera 35.
[0012]
A development image is determined. When using as an image for a development view, the process proceeds to development drawing creation, and when not used, the process proceeds to video data end determination described later.
When using as a development image, the omnidirectional sensor development correction processing unit 44 performs correction processing, and then performs image data development processing based on the above-described development processing method. Since the wall surface 11 of the tube rod 10 was photographed using the fisheye lens 61 as an omnidirectional sensor, in order to create a correctly developed view, the unfolding correction processing unit 44 corrects the tube rod depth direction, corrects the center point, and tilts. Perform each correction process. Since the image data expansion process is performed for each frame as shown in FIG. 10A, as the image after the expansion process becomes deeper in the tube, information becomes insufficient and the image is distorted. In the developed view shown in FIG. 10A, 57 is a joint, 58 is a crack, 59 is a water surface, and 60 is dirt. The developed image data for each frame is stored in the developed data storage unit 45.
[0013]
After the development process, in order to remove the distorted portion, as shown in FIG. 10B, the development images for a plurality of frames are synthesized. At the time of synthesis, since the center point of the tube 10 may be different for each image, the data matching unit 46 performs data matching.
As shown in FIG. 10C, the development drawing creation unit 47 re-inputs character information such as the position in the tube obtained from the character recognition processing unit 56 into the synthesized image.
The development view information obtained in this way is stored in the development view storage unit 48.
The development chart information obtained from the development chart processing device 37 is displayed on the monitor 54 via the development chart output unit 53 of the development chart output device 39 and printed out by the printer 55.
[0014]
Determine whether the video data ends. If the total number of images to be captured does not reach a set number (for example, 100), the image data capturing operation is repeated. When the total number of images to be captured reaches 100, the process is terminated.
[0015]
In the above, a fisheye lens is used as the omnidirectional sensor 61. In addition, an nth-order curved surface such as a circle, an ellipse, a paraboloid, a cone, etc. including a two-leaf hyperboloid mirror (n is 1 or more) It may also be a mirror or case consisting of a positive integer).
[0016]
[Problems to be solved by the invention]
When determining an abnormal location using the apparatus described in the above-mentioned publication, a development drawing is created, and the presence / absence of the abnormal location is determined on the screen or printed out.
However, when judging a place that seems to be an abnormal part, it may be difficult to determine whether there is a scratch or it may be longer than expected, depending on how the light is reflected. It is not possible to make an appropriate judgment until after the operation is printed and the development drawing is printed out, and from the development drawing, it is difficult to determine whether the location is abnormal or not unless it is a specific expert. There was a problem that the distance and angle could not be specified accurately.
Therefore, it is possible to make a decision to find an abnormal part in a moving image while continuously moving images from the camera before the development view processing and a decision in the development view in parallel on the computer, and the same in the past There has been a demand for an apparatus and a method that can store the data of one tube or another tube as a database, and can take it out at any time for comparison.
[0017]
In the present invention, when an abnormal part is found in a moving image while continuously moving the image by the camera before the development view processing, the position information of the point can be registered by checking on the image, and the abnormality is detected. An object of the present invention is to provide a tube inspection / diagnosis support device, a tube inspection / diagnosis support method, and a storage medium storing a tube inspection / diagnosis support program that can be recognized as a line when the parts are continuous. To do.
[0018]
[Means for Solving the Problems]
The present invention comprises means for reproducing and displaying as a moving image based on image data with different image frame numbers of the tube video data, means for attaching mark points on the display image, means for setting the registered image frame number, Means for registering image diagnostic information on a display image with a mark point; means for determining the pipeline distance of the registration point from the distance from the reference point of the image frame number and the position coordinates of the mark point on the display image; A point corresponding to the registered point of the image frame is obtained by calculation at a corresponding position in a different image frame, and a mark point is displayed at the obtained position, and the mark point moves as the moving image moves This is a device for assisting in diagnosis and diagnosis of a tube.
[0019]
With this configuration, the marked point appears to move when played back as a video, so it is easy to recognize the abnormal part once diagnosed, and the abnormal part can be reliably identified without special training. Can be found.
[0020]
DETAILED DESCRIPTION OF THE INVENTION
An embodiment of the present invention will be described with reference to FIGS.
First, the configuration of the in-pipe inspection diagnosis support apparatus according to the present invention will be described with reference to FIG.
The memory 80 stores the system program 1, image data 87, and table 88, and exchanges necessary data with the CPU 81. The image data 87 is obtained from the pipeline video data 86 such as actual image data that is an actual photographed image as shown in FIG. 13A and developed image data that has been processed as shown in FIG. 13B. Are taken into the memory 80 of the personal computer, and the tube fistula is diagnosed using these image data 87. The table 88 represents various table structures in the system program 1, and the captured image data is managed by the data structure of the table 88.
[0021]
This data structure includes, for example, a video header (stores and manages common data of an image captured at one time), a pipe information header (stores and manages unique data of each pipe), and survey information (each pipe Save and manage information at the time of investigation), manhole information (store and manage the manhole information of each pipeline), image diagnostic environment setting value (store the state at the time of investigation diagnosis), image These include frame information (managing frame information of captured image data), image diagnosis information (managing diagnostic information of captured image data), index information (managing index information registered at the time of examination diagnosis), and the like.
[0022]
An input device 83, a display device 84, and an output device 85 are coupled to the CPU 81 via an input / output control unit 82.
The input / output control unit 82 plays a role of sending a signal from the input device 83 to the CPU 81 and sending a calculation result by the CPU 81 to the display device 84 and the output device 85. The input device 83 includes a mouse, a keyboard, etc., the display device 84 includes a personal computer display, a TV screen, and the like, and the output device 85 includes a printer.
The system program 1 is read into the memory 80, and program information is sent from the memory 80 to the CPU 81 to perform arithmetic processing and start up the program 1. Thereafter, various processes such as image reproduction, image diagnosis, and input of diagnostic information are performed by the CPU 81 in accordance with signals from the input device 83, and the results are output to the display device 84 and the output device 85 each time. Based on the output result, the diagnostician performs a comprehensive diagnosis of tube fistula.
[0023]
The system program 1 includes an in-pipe inspection diagnosis work support program 1 of the present invention shown in FIG. This in-pipe inspection / diagnosis work support program 1 includes a result of the on-site inspection (hereinafter referred to as “pipe video data”), and a developed view (hereinafter referred to as “diagnostic information” and “pipe video data”). The diagnostic data input / output processing unit 2 and the diagnostic support processing unit 3 are used for making a video inspection diagnosis in the office and creating a survey result (hereinafter referred to as a form). , A diagnosis result input processing unit 4, a form display / print processing unit 5, a form management information input processing unit 6, and a diagnostic information list display / print processing unit 7.
[0024]
The form display / print processing unit 5 is for displaying and printing a form based on diagnosis information created based on the diagnosis result.
The form management information input processing unit 6 is used to edit the investigation subject name, investigation location, investigator, pipeline information, human hole information, etc.
The diagnostic information list display / print processing unit 7 is for displaying and printing the diagnosed information list.
[0025]
The diagnostic data input / output processing unit 2 is used to input and output pipeline video data, development views, and form data, and inputs data such as tube data to be diagnosed and tube data being diagnosed.・ Diagnosis related to functions that perform output processing and input / output of existing form data, input / output processing of form data, and diagnostic data, form data, and pipelines stored in the database (DB) It consists of DB diagnosis, form data, pipeline video data, and development process output processing related to the function of processing video data and development drawings to be output to a display or printer.
[0026]
The diagnosis support processing unit 3 is for performing moving image display and image processing of pipeline video data for diagnosis, and is configured as follows.
The index registration relates to a function of indexing images so that specific pipeline video data can be searched / displayed at high speed. When the “Register Index” button is clicked, an “Image Index” window is displayed. Information on the currently displayed image is set in the image and camera angle. When the image name classification is selected from the fixed items or set manually and registered in the image, the image name (image name classification + distance) is displayed, “Comment” is input, and the “OK” button is clicked. The distance, camera angle, and comment are stored.
When selecting a fixed item for image name classification, the following items can be selected.
"Damage""Crack""Seammisalignment""Corrosion""Saggingmeandering""Intrusionwater""Mounting pipe protruding""Motalsticking""Lard sticking root entry""Step""Mounting pipe right""Mounting pipe left""Joint""Other".
Items set and registered by manual input can be selected as selection items at the next registration.
[0027]
The index display relates to a function for displaying a list of images registered by the registration of the index, and searching for and displaying a target image at high speed, and displays image information in the following display area.
(1) “Image name list” list box: A list of index image names is displayed.
(2) View area: Displays a view of the selected image.
(3) Image name display area: Displays the selected image name.
(4) Distance display area: Displays the distance of the selected image.
(5) Angle display area: Displays the angle of the selected image.
(6) Comment display area: Displays a comment for the selected image.
(7) “Display button”: When this button is clicked, the selected image is displayed in the “index image display” window.
(8) “Delete from list” button: (1) When an image name is selected in the “image name list” and this button is clicked, the image is deleted from the index image after the confirmation message is displayed.
(9) “Video data display” button: When this button is clicked, the list is closed and the currently selected image is displayed in the pipeline video data image.
[0028]
The image diagram display relates to a function for grasping which part in the pipeline the currently displayed image is taken. In addition, the image can be enlarged by selecting a range, and this function is useful for making it easy to grasp which part of the pipeline is enlarged.
[0029]
In the superimposed data display, an “investigation distance display” window is displayed on the screen. This “survey distance display” window includes, for example, “abnormal classification”, “rank information”, “abnormal situation”, “distance”, “camera angle”, “continuous abnormal state”, and the like.
[0030]
In the survey distance display, the survey distance is displayed / hidden by selecting a menu in the superimposed data display. By displaying the “investigation distance display position setting” window, it is possible to select which part of “upper left”, “lower left”, “upper right”, and “lower right” is displayed on the screen.
[0031]
The scale display displays / hides the scale 90 as shown in FIG. 6 on the screen of the pipeline video data. By displaying the “scale value setting” window, the scale interval can be set in the range of 5 to 30 mm. By displaying the scale 90, the size of an abnormal part such as a scratch can be determined.
[0032]
In the tube bottom angle display, as shown in FIG. 6, the tube bottom angle 91 is displayed / hidden on the screen of the pipeline video data. By displaying a “tube bottom angle display” window (not shown), the tube bottom angle 91 can be set in the range of 0 to 359 degrees.
[0033]
In the abnormality diagram display, the registered abnormality diagram (mark point 92 attached to the abnormal location, connecting line 93 of the plurality of mark points 92, etc.) is displayed / hidden. While switching between display / non-display on the screen, it is possible to check whether the position of the mark point 92 is correct or whether the abnormal part is correctly marked.
[0034]
The display of the moving image relates to a function for displaying a moving image when switching to the moving image display on the deck controller screen shown in FIG. 6. The display of “normal moving image”, the display of “diagnostic moving image” (described later), “ The display of “index movie” (described later) is reproduced.
[0035]
Image enlargement / reduction processing is related to the function that enlarges the image, reduces it to grasp the whole, or restores it when you want to see the abnormal part in more detail on the currently displayed still image. Is. Further, when switching to the moving image display during the enlarged or reduced display on the still image, the moving image is displayed while being enlarged or reduced.
[0036]
The image sharpness / brightness / darkness display relates to a function for adjusting the sharpness of the image and the contrast of the image, and can be adjusted by this function when the image is difficult to see. Selecting the “Standard” button returns to the original setting.
[0037]
In FIG. 6, the deck controller operation processing includes selection of a moving image type (normal image, diagnostic image or index image), stop / playback operation of the selected display moving image, jump display to the target image, moving image moving direction / It relates to functions such as speed and travel distance settings.
[0038]
The diagnostic result input processing unit 4 is configured as follows. The diagnostic result input processing unit 4 performs processing for inputting diagnostic information registration, index registration, and form management information editing.
[0039]
In the edit selection process, a “diagnosis information registration” window shown in FIG. 6 is displayed, and “new registration”, “edit” (editing diagnostic information registered in the past), and “deletion” (past) in “edit selection” are displayed. Delete the diagnostic information registered in (1) and proceed with the examination diagnosis work.
[0040]
The diagnosis location mouse selection processing relates to a selection processing function for attaching mark points 92 to abnormal locations with a mouse.
[0041]
The registration of the abnormal classification relates to an operation for selecting and registering the classification of the detected abnormal part from the predetermined abnormal classification. Abnormal classification includes, for example, breakage, cracks, seam deviation, corrosion, sagging meandering, intruding water, protruding protruding pipe, mortar adhesion, lard adhesion, root intrusion, step, mounting pipe right, mounting pipe left, etc. Select from these and register.
[0042]
The registration of rank information is for ranking the size of the abnormal part. “Special A”: particularly large, “A”: for example, a size of 5 mm or more, “B”: for example , Having a size of 2 to 5 mm, “C”: for example, having a size of 2 mm or less, “others”: driftwood other than cracks, etc.
[0043]
The registration of the abnormal situation is performed by selecting and registering an abnormal situation suitable for the situation of the abnormal part from the predetermined abnormal situations. Abnormal conditions include, for example, mounting pipe, mounting pipe right, mounting pipe left, mounting pipe protruding, breakage, crack, seam shift, corrosion, sagging meander, intrusion water, mortar adhesion, lard adhesion, root intrusion, step, etc. Yes, select from these and register.
[0044]
The registration of detailed information is for inputting detailed information regarding the abnormal part. Click the “Detail input” button to display the “Detail input” window, and register the noticed point regarding the abnormal part as a comment.
[0045]
The distance / angle editing process relates to a function for displaying the distance and camera angle of an image for registering diagnostic information on the diagnostic result input screen. This is a value already determined at the time of shooting, and cannot be changed.
[0046]
In the abnormal diagram display / non-display designation process, when registering an abnormal diagram display, by checking a check box, the diagnostic diagram can be displayed as an enlarged diagram when the form is displayed. That is, the present invention relates to a function for selecting whether or not to display an image that is currently being registered for diagnosis as a diagnostic chart when collecting the diagnosis results of tube fistula as a form.
[0047]
In FIG. 6, the registration process is performed by adding mark points 92 (for example, x marks) to the abnormal portions of the image and using diagnostic information such as the abnormality classification, rank information, abnormality status, and detailed information. Is related to the function of
・ Individual registration: Display the image and the "Register diagnostic information" window on the screen.
Procedure 1. A mark point 92 is attached by clicking with the mouse on the abnormal part of the image.
It can be erased with the clear button.
Procedure 2. Enter "Abnormality classification", "Rank information", "Abnormal status", and "Detailed information" in the "Diagnostic information registration" window as follows.
Procedure 3. Click the “Register” button in the “Diagnostic Information Registration” window to register the input information.
Continuous registration: Mark two or more abnormal mark points 92, 92,... Per image.
Procedure 1.2.3. Is the same as the single registration described above, and the mark points 92 are sequentially connected by a connecting line 93.
-Continuous registration: A mark point 92 of an abnormal part is attached to a plurality of images.
Procedure 1. Single registration procedure the same as.
Procedure 2. Move to an image with an abnormal part in the “Deck Controller” window.
Procedure 3. Single registration procedure the same as. Procedure 1 if necessary. And 2. repeat.
Procedure 4. Single registration procedure 2. the same as.
Procedure 5. 2. Single registration procedure the same as.
[0048]
In the diagnostic information display process, a “diagnosis information registration” window is displayed in FIG. 6, “edit” is selected, and an image having an abnormal part to be edited is displayed. In the image, the “point movement” button, “point addition”, “point deletion” button, and “sensor removal” button perform respective functions.
[0049]
The form display / print processing unit 5 is configured as follows. The form display / print processing unit 5 relates to a function of displaying a form created by diagnosing pipeline video data on a display and a process of printing the form. In the form, a development view of an image registered as an abnormal part, a diagram in which the abnormal part is drawn from the diagnosis information, and a designated abnormality diagram are displayed.
[0050]
In the form display process, when the “display form” window is opened, as shown in FIG. 7, various abnormality diagrams (development diagrams, pipeline diagrams, abnormality diagrams, etc.) based on the diagnostic information are drawn on the screen.
[0051]
When the “print” window is opened, the form print processing unit prints the drawn form.
[0052]
In the form image saving process, a form is named and saved by a “form image save” button.
[0053]
The enlarged / reduced display of the form enlarges / reduces the developed view and the abnormal view while displaying the form.
[0054]
The distance display of the mouse position displays the distance information of the position where the mouse is placed when the mouse is placed and clicked on a certain point on the development view.
[0055]
In the enlarged view display by selecting the diagnosis location, the range is selected on the moving image and the enlarged view is displayed.
[0056]
The enlarged view of the diagnostic diagram displays an enlarged view of the diagnostic image.
[0057]
In the reversed display of the form, normally, a development view of the image taken from the left side to the right side is connected and displayed on the form, but this direction is reversed and displayed.
[0058]
The form management information input processing unit 6 relates to a function of creating detailed form management information by filling in detailed information on the management when creating a form, and is configured as follows.
[0059]
Editing the form management information is for displaying the "form management information" window and registering the description items necessary for form management. The investigation subject, investigation place, investigation year, judge name, presence of improvement work It is useful for management by registering information such as inability to investigate, pipeline information, form image, TV camera information, and upstream and downstream human holes as human hole information.
[0060]
The form image display designation is for determining the display method of the development view to be displayed on the form. The start position coefficient, display distance, development angle, pipe joint position, pipe node length, reverse display start distance, etc. Fill in and create a form image.
[0061]
The diagnostic information list display / print processing unit 7 relates to a function that allows a list of all diagnostic information registered with the surveyed tube based on the diagnostic information registered for the diagnosed image. The configuration is as follows.
[0062]
In the diagnostic information list display, numbers are assigned in the order in which diagnostic information is registered, and numbers, anomaly diagram display designation fields, distance, camera angle, anomaly classification, rank, and anomaly status are displayed.
[0063]
Diagnostic information tabulation display is an abnormality classification and a tabulation table for each specific item of the abnormality classification created so that you can see at a glance which abnormality classification is common and which rank is large. It is.
[0064]
In order to designate an abnormal diagram display on a form, an image to be displayed as an abnormal diagram on a form is selected and displayed when a check is entered in the abnormal designation display designation column in the list displayed in the diagnosis information display.
[0065]
A specific flow of performing diagnosis using the intra-pouch examination diagnosis support program according to the present invention will be described with reference to FIGS.
First, in FIG. 1, registration of diagnostic information is performed. For this purpose, the pipeline video data 86 in FIG. 3 is read as image data 87 into a memory 80 such as a hard disk of a personal computer. Also, the system program 1 is activated. The system program 1 opens the image data 87 of the pipeline video data 86 and displays the “deck controller” window (a in FIG. 1 and FIG. 6). The “deck controller” is operated to reproduce and display the duct video data 86 (b in FIG. 1 and FIG. 6).
[0066]
The “deck controller” reproduces and displays the image frame information 1, 2,... M of the pipeline video data 86 shown in FIG. It can be continuously played back as a moving image as if moving backward. For more details,
(1) A display image is displayed on the screen based on the image name in the image frame information shown in FIG.
(2) The distance range of the pipeline shown in the displayed image is obtained based on the characteristics of the mirror lens of the camera, the radius of the examination pipeline, and the image shooting distance in the image frame information.
(3) The obtained distance range of the pipeline is compared with the pipeline distance recorded in the diagnostic imaging information shown in FIG. 2B, and the contents of the relevant diagnostic imaging information are displayed on the screen.
In addition to moving images, each frame can be viewed as a still image.
[0067]
First, an image to be reproduced as a moving image and registered for diagnosis is searched. When a possible portion as an abnormal part is found (c in FIG. 1), the operation is switched to a still image and a detailed diagnosis is performed. When an abnormal location is clicked with the mouse button (FIG. 1D), the image diagnostic information shown in FIG. 2B is created, and the mouse position coordinates are temporarily registered in the column (1) of FIG. The image frame number at that time is also automatically recorded in the column of FIG. 2B from the image frame information of FIG. A mark point 92 (x mark) is displayed on the screen. Here, registration continues while there is an abnormality? Becomes YES, and the process returns to b of FIG.
[0068]
Next, continue registration? If NO, the diagnostic information window is opened, the diagnostic information is entered (f in FIG. 1), and the diagnostic information is set.
In setting diagnosis information, as shown in FIG. 1. Selection of abnormality classification 2. Selection of rank information 3. Selection of abnormal situation Enter detailed information.
1. For the abnormal classification, as shown in the registration of the abnormal classification, breakage, cracks, seam deviation, corrosion, sagging meandering, intrusion water, mounting pipe protrusion, mortar adhesion, lard adhesion root penetration, step, mounting pipe right, installation There are other pipes on the left, and you can choose from these.
2. The rank information is treated as “special A”, “A”, “B”, “C”, “other” as shown in the registration of the rank information.
3. The abnormal situation is as shown in the registration of the abnormal situation, mounting pipe, mounting pipe right, mounting pipe left, mounting pipe protruding, breakage, crack, seam deviation, corrosion, sagging meander, intrusion water, mortar adhesion, lard adhesion tree There are root intrusions and steps, and you can choose from these.
4). For the detailed information, the points that are noticed regarding the abnormal part are registered as comments.
[0069]
While there is no change in the setting contents of the diagnostic information, while this is NO, this is repeated. When YES is confirmed (g in FIG. 1), the registration button is selected (h in FIG. 1), and the registration is terminated. When the registration button is selected, the abnormal location failure status and registration status are registered in (3) and (5) in FIG. The pipeline distance of the registration point (4) is obtained from the distance of the image frame number and the mouse position coordinates and registered.
Here, in the registration state in (5), 0 is set in the case of single registration in the registration process. For continuous registration, 1 is set for a continuous start point, 2 is set for continuous registration, and 3 is set for a continuous point end point.
[0070]
The image frame including the mark point 92 and the connecting line 93 registered as described above is displayed as a development view on the form, and the image frame can also be displayed as an abnormality diagram. Further, the mark point 92 and the connecting line 93 are obtained by calculation at corresponding positions in different image frames, and the mark point is displayed at the obtained position.
For example, in FIG. 4A, the camera finds a flaw in the image at the position a, and the image with the mark point 92 and the connecting line 93 is registered as shown in FIG. To do. The position of the mark point 92 and the connecting line 93 in the image of (C) is recognized after being converted into the space coordinates in the tube, and the position of the mark point 92 and the connecting line 93 in the space coordinates is adjacent. Whether it exists in the image frame to be obtained is obtained by calculation. If it exists, it is registered as image diagnostic information, and a mark point 92 and a connecting line 93 are displayed at the corresponding position.
Therefore, if the camera moves to the position b as shown in FIG. 4B, the position of the flaw also moves, but the position of the spatial coordinates is registered when the camera is at the position a in FIG. 4B, the mark point 92 and the connecting line 93 are automatically displayed in the image frame at the position b of the camera in FIG.
By using this method, the registered mark point 92 and the combined line 93 are also displayed in other image frames, and the mark point 92 and the combined line 93 move together when viewed as a moving image. It will be visible. As shown in FIG. 4D, since the mark point 92 and the connecting line 93 are all displayed in the image frame while the camera position moves from a to b, the scratches appear to move as shown in the figure. .
[0071]
When the pipeline video data is diagnosed to the end and the diagnostic information registration is completed, a form is created. The display distance range and the development angle of the development view displayed on the form can be designated by the form image display designation and set so as to be easily evaluated. Further, form management information is created by editing the form management information, and the entire evaluation is performed as a diagnosis result. For example, as shown in FIG. 7, a developed view, a pipeline view, and an abnormality view are displayed.
[0072]
The pipeline video data and the form are stored as a database (DB). Here, if all the pipeline video data is to be stored, the capacity becomes too large and a very large DB size is required. Therefore, it is desired to reduce the capacity by thinning out image frames in the pipeline video data.
This image frame reduction method will be described with reference to the flowchart shown in FIG.
(A) First, a thinning interval and a storage destination are designated. At this time, the specified interval counter = 0.
(B) The first image and image frame information are stored unconditionally.
(C) Next, confirm that it is not the last image frame.
(D) If it is not the last image frame, +1 is added to the designated interval counter.
(E) After adding +1, the next image frame information is set as a processing target.
(F) It is checked whether or not this image frame information is related to image diagnostic information.
(H) If there is a relationship with the image diagnosis information, the specified interval counter = 0.
(I) The image and image frame information are saved, and the process returns to (c).
(G) When there is no relation with the image diagnosis information, it is checked whether or not the specified interval counter> thinning interval.
(H) If the designated interval counter is larger, the designated interval counter = 0.
(I) The image and image frame information are saved, and the process returns to (c).
If the thinning interval is larger in (g), the process returns to (c).
If the above processing is continued, an image whose image frame information is not related to image diagnostic information is processed without being saved, and the capacity is reduced. However, if all images that are not related to the image diagnosis information are not saved, the continuity as a moving image is lost. Therefore, a thinning interval is set, and when a certain interval is left, one image is saved.
For example, in the case of processing to drop a frame-captured image of 30 frames / second to 1 frame / second, if the processing of discarding 29 frames, leaving 1 frame in order from the front, is performed, event information (abnormal information, The frame in which the event information is registered is checked from the next frame to the 29th frame determined as the storage frame, and the event information is registered. If not, all are discarded. If there is, the frame in which the event information is registered is left, and the same processing is repeated for the next frame to the 29th frame.
[0073]
【The invention's effect】
According to the present invention, means for reproducing and displaying as a moving image based on tube video data, means for attaching a mark point on a display image, means for registering a registered image frame number, and determining a pipeline distance of the mark point Therefore, the marked point appears to move when reproduced as a moving image, and even an amateur can more easily recognize an abnormal part.
[0074]
Since there is a means for registering diagnostic imaging information on the display image with the mark point, selection of preset abnormality classification, selection of preset rank information, selection of preset abnormal situation and arbitrarily Detailed information that can be entered can be registered. In addition, a form can be created instantaneously using an image frame in which diagnostic information is registered.
[0075]
Since the point corresponding to the registered point of the registered image frame is obtained by calculation at a corresponding position in a different image frame and the mark point is displayed at the obtained position, the mark point is also changed as the moving image is moved. It can be moved.
[0076]
By having a function of connecting a plurality of mark points with bond lines, the length, shape, width, etc. of the crack can be recognized at a glance.
[0077]
By registering image frames having event information and image frames at predetermined intervals among image frames having no event information and deleting the remaining frames, the storage capacity of the database can be reduced. Moreover, there is no problem due to lack of events.
[Brief description of the drawings]
FIG. 1 is a flowchart for diagnosing pipeline video data using the method for supporting diagnosis of in-pipe inspection according to the present invention.
2A is an explanatory diagram of image frame information, and FIG. 2B is an explanatory diagram of image diagnosis information.
FIG. 3 is a block diagram showing an embodiment of an intraductal examination diagnosis support device according to the present invention.
FIG. 4 shows the correspondence between the position of a camera and duct video data when the in-tube inspection / diagnosis support apparatus according to the present invention is used. FIG. 4 (A) is a partially cutaway view of a photographing state at point a. (B) is a partially cutaway perspective view of the shooting state at point b, (C) is a camera image at point a, and (D) is a camera image at point b. FIG.
FIG. 5 is an explanatory diagram showing a configuration of a tube inspection and diagnosis work support program 1 according to the present invention.
FIG. 6 is a front view of an example of an index image displayed by using the intratracheal examination diagnosis support device according to the present invention.
FIG. 7 is a front view of an example of a form displayed using the in-tube inspection / diagnosis support apparatus according to the present invention.
FIG. 8 is a flowchart for explaining a method of thinning out the number of image frames in the method for supporting diagnosis within a tube according to the present invention.
FIG. 9 is a block diagram showing a processing device for an inner surface image of a trocar described in the publication.
FIGS. 10A and 10B show an order of development of a developed view by the processing device for the inner surface image of the tube in FIG. 9, wherein FIG. 10A is a developed view for one frame, FIG. c) is a development view after adding damage information.
11A and 11B are diagrams for explaining the processing device for the inner surface image of the tube rod shown in FIG. 9, wherein FIG. 11A is an explanatory view showing a state in which a fisheye lens 61 as an omnidirectional sensor is attached to the tip of the video camera 35; ) Is an explanatory diagram of the maximum shooting angle αmax, the minimum shooting angle αmin, and the visible range, and (c) is a projection view of an image displayed on the video camera 35.
12 is a perspective view of a state in which the video camera 35 in FIG.
FIG. 13A is a real image data diagram before development of the actual tube rod 10, and FIG. 13B is a development diagram after development.
14A and 14B show another embodiment of the main part of the processing apparatus for the inner surface image of the tube pod in FIG. 9, in which FIG. 14A is an explanatory diagram for displaying a fisheye lens front monitoring image, and FIG. An explanatory diagram of a state in which the wall surface image 75 and the forward monitoring image 74 are projected on the screen 69, (c) is an explanatory diagram in which the forward monitoring image 74 is magnified, and (d) is an enlarged area of the forward monitoring image 74. It is explanatory drawing projected.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 ... Tubular inspection diagnostic work support program, 2 ... Diagnostic data input / output processing unit, 3 ... Diagnosis support processing unit, 4 ... Diagnosis result input processing unit, 5 ... Form display / print processing unit, 6 ... Form management information input processing unit, 7 ... Display / printing processing unit for diagnosis information list, 10 ... Tube, 11 ... Wall surface, 14 ... Crack, 14a ... Crack on actual tube 10, 14b ... Video camera 35 Image crack, 14c ... Development view crack, 35 ... Video camera, 36 ... Video data input device, 37 ... Development view processing device, 39 ... Development view output device, 40 ... Video deck, 41 ... Video capture board, 42 ... Image data storage unit 44 ... Development correction processing unit 45 ... Development data storage unit 46 ... Data matching unit 47 ... Development drawing creation unit 48 ... Development drawing storage unit 53 ... Development drawing output unit 54 ... Monitor 55 ... printer, 56 ... character recognition processing unit, 57 ... seam, 58 ... crack, 59 ... water surface, 60 ... dirt, 61 ... omnidirectional sensor (two-leaf hyperboloid mirror or fisheye lens), 62 ... relay lens, 63 ... Image sensor 64 ... Illuminating lamp 65 ... Reflecting surface 66 ... Transmitting surface 67 ... Reflecting surface 68 ... Incident surface 69 ... Screen 70 ... Transmitting portion 71 71 Zoom lens 72 72 Wide angle lens 73 Non Projection unit, 74 ... monitoring image, 75 ... wall image, 80 ... memory, 81 ... CPU, 82 ... input / output control unit, 83 ... input device, 84 ... display device, 85 ... output device, 86 ... pipe video data, 87 ... image data, 88 ... table, 90 ... scale, 91 ... tube bottom angle, 92 ... mark point, 93 ... connecting line.

Claims (6)

Means for reproducing and displaying as a video based on image data with different image frame numbers of the video data;
Means for marking on the display image;
Means for setting the registered image frame number;
Means for registering image diagnostic information on a display image with a mark point;
Means for determining the pipeline distance of the registration point from the distance from the reference point of the image frame number and the position coordinates of the mark point on the display image;
Means for calculating a point corresponding to the registered point of the registered image frame at a corresponding position in a different image frame, and displaying the mark point at the determined position, and the mark point is changed as the moving image is moved. An in-pipe inspection diagnosis support device characterized by being moved. It means for marking points on the displayed image according to claim 1 Symbol mounting tube culvert in laboratory diagnosis support apparatus characterized by having a function for connecting the plurality of mark points in the coupled line. The means for registering diagnostic imaging information on a display image with a mark point can select a preset abnormality classification, select preset rank information, select a preset abnormal situation, and arbitrarily input pipe culverts in laboratory diagnosis support apparatus according to claim 1, characterized in that it has a function of registering the detailed information.   Playback and display as a movie based on image data with different image frame numbers in the management video data, add mark points on this display image, set the registered image frame numbers, and display on the display image with the mark points The image diagnostic information is registered, the pipeline distance of the registration point is obtained from the distance from the reference point of the image frame number and the position coordinates of the mark point on the display image, and the point corresponding to the registration point of the registered image frame is An intraductal inspection diagnosis support method characterized in that a calculation is made at a corresponding position in a different image frame, a mark point is displayed at the obtained position, and the mark point is moved as the moving image is moved. The image frames with different image frame numbers in the management video data are registered as image frames having mark points and other event information and image frames at predetermined intervals among image frames having no event information. 5. The method for supporting diagnosis within a tube according to claim 4, wherein the method is deleted. The computer, according to claim 1 to 5 in any one the stored storage medium pipe culverts in laboratory diagnosis support program for realizing the functions described.

Images