Pipeline condition determination device, pipeline condition determination method, and pipeline condition determination program

Abstract

To accurately detect abnormalities occurring inside a pipeline. [Solution] A pipeline condition determination device comprising: a forward-view internal image acquisition unit that acquires a forward-view internal image taken by a self-propelled robot cart equipped with at least one camera capable of imaging the inside of a pipeline while the robot cart travels inside the pipeline with the camera pointed in the direction of travel of the self-propelled robot cart; a suspected abnormal area identification unit that identifies a suspected abnormal area occurring inside the pipeline based on the forward-view internal image; a travel control unit that moves the self-propelled robot cart to a position near the suspected abnormal area; a camera control unit that points the camera in a direction perpendicular to the direction of travel when the self-propelled robot cart reaches a position near the suspected abnormal area and the suspected abnormal area is no longer visible in the forward-view internal image; a side-view internal image acquisition unit that acquires a side-view internal image taken by a camera pointed in a direction perpendicular to the direction of travel; and an abnormal state determination unit that determines the abnormal state of the suspected abnormal area based on the side-view internal image.

Description

Technical Field

[0001] The present invention relates to a pipeline state determination device, a pipeline state determination method, and a pipeline state determination program.

Background Art

[0002] In the above technical field, Patent Document 1 discloses that an image of a specified one frame of an input video and an image in which a video analysis result for the image is superimposed are displayed in parallel so as to be easily compared, and in-pipe diagnosis is easily performed (paragraphs

[0153] to

[0157] of the same document, FIG. 18, etc.).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the technique described in Patent Document 1 above, video analysis is performed based on a video captured by a camera directed in the extending direction of the pipe, and in-pipe diagnosis is performed. Therefore, it has not been possible to accurately determine an abnormality occurring inside the pipeline.

Means for Solving the Problems

[0005] To achieve the above object, a pipeline state determination device according to the present invention A forward-view internal image acquisition unit that acquires a forward-view internal image obtained by imaging the camera in the traveling direction of the self-propelled robot cart while the self-propelled robot cart equipped with at least one camera capable of imaging the inside of the pipeline travels inside the pipeline; A suspected abnormal region specifying unit that specifies a suspected abnormal region occurring inside the pipeline based on the forward-view internal image; A driving control unit that moves the self-propelled robot carriage to a position near the suspected abnormality area, When the self-propelled robot carriage reaches a position near the suspected abnormal part and the suspected abnormal part is no longer visible in the forward-view internal image, the camera control unit directs the camera in a direction perpendicular to the direction of travel, A side-view internal image acquisition unit acquires a side-view internal image captured by the camera, which is oriented in a direction perpendicular to the direction of travel, An abnormal state determination unit that determines the abnormal state of the suspected abnormal region based on the side view internal image, It is equipped.

[0006] Furthermore, in order to achieve the above objective, the pipeline condition determination method according to the present invention is: A forward-view internal image acquisition step involves a self-propelled robotic cart equipped with at least one camera capable of imaging the inside of a pipeline traveling through the pipeline and acquiring a forward-view internal image by directing the camera toward the direction of travel of the self-propelled robotic cart. A suspected abnormality region identification step, based on the forward-view internal image, identifies a suspected abnormality region occurring inside the pipeline, A driving control step that moves the self-propelled robot cart to a position near the suspected abnormality area, The camera control step involves orienting the camera in a direction perpendicular to the direction of travel at the moment when the self-propelled robot carriage reaches a position near the suspected abnormal part and the suspected abnormal part is no longer visible in the forward-view internal image, A side view internal image acquisition step involves acquiring a side view internal image captured by the camera oriented in a direction perpendicular to the direction of travel, An abnormal state determination step in which the abnormal state of the suspected abnormal region is determined based on the side view internal image, Includes.

[0007] Furthermore, in order to achieve the above objective, the pipeline condition determination program according to the present invention is: A forward-view internal image acquisition step involves a self-propelled robotic cart equipped with at least one camera capable of imaging the inside of a pipeline traveling through the pipeline and acquiring a forward-view internal image by directing the camera toward the direction of travel of the self-propelled robotic cart. A suspected abnormality region identification step, based on the forward-view internal image, identifies a suspected abnormality region occurring inside the pipeline, A driving control step that moves the self-propelled robot cart to a position near the suspected abnormality area, The camera control step involves orienting the camera in a direction perpendicular to the direction of travel at the moment when the self-propelled robot carriage reaches a position near the suspected abnormal part and the suspected abnormal part is no longer visible in the forward-view internal image, A side view internal image acquisition step involves acquiring a side view internal image captured by the camera oriented in a direction perpendicular to the direction of travel, An abnormal state determination step in which the abnormal state of the suspected abnormal region is determined based on the side view internal image, Have the computer execute it.

[0008] Furthermore, in order to achieve the above objective, the pipeline condition determination device according to the present invention is A forward-view internal image acquisition unit acquires a forward-view internal image taken by a self-propelled robot cart equipped with at least one camera capable of imaging the inside of a pipeline, while the robot cart travels inside the pipeline and the camera is pointed in the direction of travel of the self-propelled robot cart. A forward-view internal image acquisition unit acquires a forward-view internal image from the first camera, which captures the direction of travel of the self-propelled robot cart, while the self-propelled robot cart is traveling inside the pipe, using a self-propelled robot cart equipped with a first camera and a second camera capable of imaging the inside of the pipe, A suspected abnormality area identification unit identifies a suspected abnormality area occurring inside the pipeline based on the forward-view internal image, A driving control unit that moves the self-propelled robot carriage to a position near the suspected abnormality area, A camera control unit that switches from the first camera to the second camera at the timing when the self-propelled robot cart reaches a position near the suspected abnormal part and the suspected abnormal part disappears in the forward internal image; A side view internal image acquisition unit that acquires a side view internal image captured by the second camera directed in a direction orthogonal to the traveling direction; An abnormal state determination unit that determines the abnormal state of the suspected abnormal region based on the side view internal image; It is provided with.

Effect of the Invention

[0009] According to the present invention, it is possible to accurately determine an abnormality occurring inside a pipeline.

Brief Description of the Drawings

[0010] [Figure 1] It is a diagram for explaining an outline of determination by a pipeline state determination device according to a first embodiment of the present invention. [Figure 2] It is a block diagram for explaining the configuration of a pipeline state determination device according to a first embodiment of the present invention. [Figure 3] It is a diagram showing an example of an abnormal state determination table possessed by a pipeline state determination device according to a first embodiment of the present invention. [Figure 4] It is a diagram for explaining the hardware configuration of a pipeline state determination device according to a first embodiment of the present invention. [Figure 5] It is a flowchart for explaining the processing procedure of a pipeline state determination device according to a first embodiment of the present invention.

Modes for Carrying Out the Invention

[0011] Hereinafter, modes for carrying out the present invention will be exemplarily described in detail with reference to the drawings. However, the configurations, numerical values, processing flows, functional elements, etc. described in the following embodiments are merely examples, and their modifications and changes are free, and are not intended to limit the technical scope of the present invention to the following description.

[0012] [First Embodiment] The pipeline state determination device 100 according to the first embodiment of the present invention will be described with reference to FIGS. 1 to 5. FIG. 1 is a diagram for explaining the outline of the pipeline state determination device 100 according to the present embodiment. The pipeline state determination device 100 is a device for determining abnormalities occurring inside a pipeline 110 such as a sewer pipe.

[0013] In the inspection of the inside of the pipeline 110 such as a sewer pipe, an inspection using an internal image (inner peripheral surface image) of the pipeline 110 captured by the camera 121 of the self-propelled robot cart 120 is being performed. The operator uses a display or the like installed outside the pipeline 110 to check the image captured by the camera 121 and perform an inspection to determine whether an abnormality such as damage has occurred in the pipeline 110.

[0014] First, the operator installs the self-propelled robot cart 120 at the inspection start position of the pipeline 110 with the camera 121 facing the inspection target area side (the traveling direction side of the self-propelled robot cart 120). After that, the self-propelled robot cart 120 starts traveling while capturing images of the inside of the pipeline 110 with the camera 121.

[0015] When the self-propelled robot cart 120 starts traveling, the pipeline state determination device 100 acquires a forward view internal image 130 (an image focused on the back side of the pipeline 110) captured by the camera 121 in the traveling direction of the self-propelled robot cart 120. The pipeline state determination device 100 identifies a suspected abnormal area 131, which is an area where the occurrence of an abnormality is suspected, based on the acquired forward view internal image 130.

[0016] When a suspected abnormality area 131 is identified, the pipeline condition determination device 100 moves the self-propelled robot cart 120 to the vicinity of the suspected abnormality area 131. When the self-propelled robot cart 120 reaches the vicinity of the suspected abnormality area 131, the pipeline condition determination device 100 directs the camera 121 mounted on the self-propelled robot cart 120 toward the wall side (inner surface side) of the pipeline 110, thereby capturing a side view internal image 140 (an image focused on the wall surface of the pipeline 110). The pipeline condition determination device 100 then acquires the captured side view internal image 140 and determines the abnormality state occurring in the suspected abnormality area 131 of the pipeline 110 based on the acquired side view internal image 140.

[0017] Next, the configuration of the pipeline condition determination device 100 will be described with reference to Figure 2. The pipeline condition determination device 100 includes a forward-view internal image acquisition unit 201, a suspected abnormal area identification unit 202, a driving control unit 203, a camera control unit 204, a side-view internal image acquisition unit 205, and an abnormal condition determination unit 206.

[0018] The forward-view internal image acquisition unit 201 acquires a forward-view internal image 130 taken by a self-propelled robot cart 120 equipped with at least one camera 121 capable of imaging the inside of the conduit 110, while the cart is traveling inside the conduit 110 and the camera 121 is pointed in the direction of travel of the self-propelled robot cart 120.

[0019] Here, "pipeline 110" refers to a waterway, specifically one constructed for the purpose of water supply and drainage. For example, pipelines 110 include water supply pipes, sewer pipes, water supply pipes, and drainage pipes. The materials used for pipelines 110 include concrete, ceramics, and iron, and the types of pipelines 110 include concrete pipes, concrete concrete pipes, ceramic pipes, and iron pipes.

[0020] Furthermore, abnormalities include damage, cracks, and scratches in the pipeline 110, but also include other conditions such as water infiltration, protrusion of connecting pipes, tree root intrusion, and mortar adhesion, and shall include any condition in which the pipeline 110 cannot perform as expected.

[0021] In this embodiment, the pipe diameter of the conduit 110 is assumed to be approximately 450 mm, but it is not limited to this, and conduits 110 of various diameters can be used.

[0022] Camera 121 may be any type of camera, such as a standard camera, a wide-angle camera, or a 360-degree camera. Camera 121 may also have features such as zoom and autofocus.

[0023] The suspected abnormality region identification unit 202 identifies a suspected abnormality region 131 occurring inside the conduit 110 based on the forward-view internal image 130. Here, the suspected abnormality region 131 is an area where an abnormality is suspected to have occurred. The identification of the suspected abnormality region 131 is performed, for example, using a trained suspected abnormality region identification model obtained by training an artificial intelligence with forward-view internal images 130 that have been captured in the past. The forward-view internal images 130 that have been captured in the past have information about the type and location of the abnormality, as well as information about the abnormality, superimposed on them as text data or image data. Therefore, by training the artificial intelligence with the text data etc. together with the image of the abnormal part, a trained suspected abnormality region identification model can be obtained efficiently.

[0024] The travel control unit 203 moves the self-propelled robot cart 120 to a position near the suspected abnormality area 131. Here, the nearby position is a position where the suspected abnormality area 131 is directly beside or directly above the self-propelled robot cart 120. The travel control unit 203 controls the self-propelled robot cart 120 to move to the nearby position.

[0025] The camera control unit 204 directs the camera 121 in a direction perpendicular to the direction of travel when the self-propelled robot carriage 120 reaches a position near the suspected abnormality area 131 and the suspected abnormality area 131 is no longer visible in the forward-view internal image 130. In other words, when the frame or other indicator of the suspected abnormality area 131 disappears from the camera 121's field of view, or when it barely remains within the camera 121's field of view, the suspected abnormality area 131 is located directly beside or directly above the self-propelled robot carriage 120.

[0026] Therefore, the camera control unit 204 changes the orientation of the camera 121 at the timing when the suspected abnormality area 131 disappears from the camera 121's field of view, thereby enabling clearer imaging of the suspected abnormality area 131. The orientation of the camera 121 is approximately perpendicular to the direction of travel of the self-propelled robot cart 120, that is, the orientation such that the lens of the camera 121 is approximately directly facing the inner surface of the conduit 110. In this way, while the self-propelled robot cart 120 is traveling, the camera 121 is directed so that it is focused at infinity in the extension direction (direction of travel) of the conduit 110, but in the vicinity of the suspected abnormality area 131, its orientation is controlled so that it is focused on the inner surface of the conduit 110 (suspected abnormality area 131).

[0027] The side-view internal image acquisition unit 205 acquires a side-view internal image 140 captured by a camera 121 directed perpendicular to the direction of travel. The side-view internal image 140 is an image of the inner surface of the conduit 110, and is an image taken in a positional relationship such that the lens of the camera 121 is facing (opposing) the suspected abnormality area or the inner surface of the conduit 110. In the forward-view internal image 130, the lens of the camera 121 is directed from an oblique direction to the suspected abnormality area 131, making it difficult to accurately identify the type, size, direction, and tilt of the abnormality. Therefore, the self-propelled robot carriage 120 is brought closer to the suspected abnormality area 131, and the image used is switched according to the purpose in order to obtain a clear image by capturing the suspected abnormality area 131 from a close distance with the camera 121.

[0028] The abnormal state determination unit 206 determines the abnormal state of the suspected abnormal region 131 based on the side view internal image 140. In other words, the abnormal state determination unit 206 determines the abnormal state using a trained abnormal state determination model obtained by training artificial intelligence with side view internal images acquired in the past, and the side view internal image 140.

[0029] Here, the lateral view internal image 140 may be an image with a higher resolution than the forward view internal image 130. That is, the forward view internal image 130 is an image (screening image) used to identify the suspected abnormality region 131 and to move the self-propelled robot carriage 120 to the vicinity of the suspected abnormality region 131. In contrast, the lateral view internal image 140 is an image for identifying abnormalities such as damage, and since the abnormal state must be determined including the type of abnormality, a higher resolution image makes it possible to determine the abnormal state in more detail.

[0030] The abnormal state determination unit 206 then uses previously captured side-view internal images to train artificial intelligence and generate a trained abnormal state determination model for determining abnormal states. Previously captured side-view internal images have information about the type and location of the abnormality, such as text data and image data, superimposed on them. Therefore, by training the artificial intelligence with this text data along with the image of the abnormal area, a trained abnormal state determination model can be efficiently obtained.

[0031] Furthermore, as described above, the forward-view internal image 130 and the side-view internal image 140 may be captured using a single camera 121 while adjusting the resolution, etc., but they may also be captured separately using a camera for capturing the forward-view internal image 130 and a camera for capturing the side-view internal image 140. In other words, two cameras, a low-resolution camera for capturing the forward-view internal image 130 and a high-resolution camera for capturing the side-view internal image 140, may be mounted on the self-propelled robot carriage 120.

[0032] Furthermore, the resolution may differ depending on whether the camera 121 is capturing a forward-view internal image 130 by imaging the direction of travel of the self-propelled robot carriage 120, or whether the camera 121 is changing its orientation to capture a side-view internal image 140 by imaging the inner circumferential surface of the conduit 110.

[0033] In this explanation, we have described an example in which a single camera 121 mounted on a self-propelled robot cart 120 captures forward-view internal images 130 and side-view internal images 140. However, the number of cameras 121 mounted is not limited to one; there may be multiple cameras.

[0034] Next, an example of an abnormal state determination table 301 of the pipeline condition determination device 100 will be described with reference to Figure 3. The abnormal state determination table 301 stores a pattern 312 associated with an abnormality type 311. The abnormality type 311 is the type of abnormality and includes items such as damage, cracks, water infiltration, connecting pipes, tree root intrusion, and mortar adhesion. The pattern 312 is the shape, characteristics, and features determined according to the type of abnormality and includes direction, length, and inclination. The pipeline condition determination device 100 then uses the abnormal state determination table 301 to determine the abnormal state of the suspected abnormal region 131. As mentioned above, if the pipeline condition determination device 100 determines the abnormal state using a learned abnormal state determination model, it is not necessary to use the abnormal state determination table 301.

[0035] Referring to Figure 4, the hardware configuration of the pipeline condition determination device 100 will be described. The CPU (Central Processing Unit) 410 is a processor for arithmetic control and realizes the various functional configurations of the pipeline condition determination device 100 shown in Figure 2 by executing programs. The CPU 410 may have multiple processors and may execute different programs, modules, tasks, threads, etc. in parallel. The ROM (Read Only Memory) 420 stores initial data, fixed data such as programs, and other programs. The network interface 430 communicates with other devices via the network. Note that the CPU 410 is not limited to one, and may have multiple CPUs, or may include a GPU (Graphics Processing Unit) for image processing. Furthermore, it is desirable that the network interface 430 has a CPU independent of the CPU 410 and writes or reads transmitted and received data to or from the RAM (Random Access Memory) 440 area. It is also desirable to provide a DMAC (Direct Memory Access Controller) for transferring data between the RAM 440 and the storage 450 (not shown). Furthermore, the CPU 410 recognizes that data has been received or transferred to the RAM 440 and processes the data. The CPU 410 also prepares the processing results in the RAM 440 and leaves subsequent transmission or transfer to the network interface 430 or DMAC.

[0036] RAM440 is a random access memory used by the CPU410 as a temporary storage work area. RAM440 has a storage area reserved for storing the data necessary to realize this embodiment. Current position data441 is data about the position of the self-propelled robot cart 120 inside the pipeline 110, for example, data about how far it is from the entrance (starting point) of the pipeline 110. Camera orientation data442 is data about the direction the camera 121 is facing. Imaging data443 is data about the internal image of the pipeline 110 captured by the camera 121. Suspected abnormal area data444 is data about the position and size of the suspected abnormal area 131. Abnormal state determination data445 is data about the determined abnormal state when an abnormality occurs in the suspected abnormal area 131.

[0037] The transmitted and received data 446 is data transmitted and received via the network interface 430. The RAM 440 also has an application execution area 447 for running various application modules.

[0038] The storage 450 stores the database, various parameters, and the following data or programs necessary for realizing this embodiment. The storage 450 stores the abnormal state determination table 301. The abnormal state determination table 301 is a table that manages the relationship between abnormality type 311 and manifestation 312, as shown in Figure 3.

[0039] The storage 450 further houses a forward-view internal image acquisition module 451, a suspected abnormal area identification module 452, a driving control module 453, a camera control module 454, a side-view internal image acquisition module 455, and an abnormal state determination module 456.

[0040] The forward-view internal image acquisition module 451 is a module that acquires images of the inside of the conduit 110 by pointing the camera 121 in the direction of travel of the self-propelled robot carriage 120. The suspected abnormal area identification module 452 is a module that identifies suspected abnormal areas occurring inside the conduit 110 based on the forward-view internal image 130. The travel control module 453 is a module that moves the self-propelled robot carriage 120 to a position near the suspected abnormal area 131. The camera control module 454 is a module that points the camera 121 in a direction perpendicular to the direction of travel when the self-propelled robot carriage 120 reaches a position near the suspected abnormal area 131 and the suspected abnormal area 131 is no longer visible in the forward-view internal image 130. The side-view internal image acquisition module 455 is a module that acquires side-view internal images 140 captured by the camera 121 pointed in a direction perpendicular to the direction of travel. The abnormal state determination module 456 is a module that determines the abnormal state of the suspected abnormal region 131 based on the side view internal image 140. These modules 451 to 456 are read by the CPU 410 into the application execution area 447 of the RAM 440 and executed. The control program 457 is a program for controlling the entire pipeline condition determination device 100.

[0041] The input / output interface 460 interfaces with input / output data from input / output devices. The display unit 461 and the operation unit 462 are connected to the input / output interface 460. A storage medium 464 may also be connected to the input / output interface 460. Furthermore, a speaker 463 which is an audio output unit, a microphone (not shown) which is an audio input unit, or a GPS position determination unit may also be connected. Note that the RAM 440 and storage 450 shown in Figure 4 do not contain programs or data related to the general-purpose functions of the pipeline condition determination device 100 or other feasible functions.

[0042] Next, the processing procedure of the pipeline condition determination device 100 will be explained with reference to the flowchart shown in Figure 5. This flowchart is executed by the CPU 410 in Figure 4 using the RAM 440, and realizes the various functional configurations of the pipeline condition determination device 100 in Figure 2.

[0043] In step S501, the forward-view internal image acquisition unit 201 acquires a forward-view internal image 130 taken by a self-propelled robot cart 120 equipped with at least one camera 121 capable of imaging the inside of the pipeline 110, while the robot cart 120 travels inside the pipeline 110 with the camera facing the direction of travel of the self-propelled robot cart 120. In step S503, the suspected abnormal area identification unit 202 determines whether or not a suspected abnormal area 131 occurring inside the pipeline 110 has been identified based on the acquired forward-view internal image 130. If the suspected abnormal area 131 has not been identified (NO in step S503), the pipeline condition determination device 100 returns to step S501. If the suspected abnormal area 131 has been identified (YES in step S503), the pipeline condition determination device 100 proceeds to step S505.

[0044] In step S505, the travel control unit 203 controls the self-propelled robot carriage 120 to move to a position near the identified suspected abnormality area 131. In step S507, when the self-propelled robot carriage 120 reaches a position near the suspected abnormality area 131 and the suspected abnormality area 131 is no longer visible from the forward-view internal image 130, the camera control unit 204 directs the camera 121 in a direction perpendicular to the direction of travel of the self-propelled robot carriage 120 so that the inner surface of the conduit 110 can be imaged by the camera 121.

[0045] In step S509, the side-view internal image acquisition unit 205 acquires a side-view internal image 140 (an image of the inner surface of the conduit 110) captured by the camera 121 whose imaging direction has been changed. In step S511, the abnormal state determination unit 206 determines the abnormal state of the suspected abnormal region 131 based on the acquired side-view internal image 140. In step S513, the conduit state determination device 100 determines whether the abnormal state determination has been completed for the entire length of the conduit 110. If it is determined that the determination has not been completed (NO in step S513), the conduit state determination device 100 returns to step S501. If it is determined that the determination has been completed (YES in step S513), the conduit state determination device 100 terminates the process.

[0046] According to this embodiment, abnormalities occurring inside the pipeline can be determined with high accuracy. Furthermore, by training the artificial intelligence with previously captured images and superimposed text data, a trained model is generated, enabling highly accurate detection of abnormal conditions. For searching for suspected abnormal areas, forward-view internal images are used, and for determining abnormal conditions, side-view internal images are used, allowing for the use of different images depending on the purpose, thus enabling even more accurate detection of abnormal conditions.

[0047] Although the present invention has been described above with reference to embodiments, the present invention is not limited to the embodiments described above and can be modified as appropriate. Various modifications to the configuration and details of the present invention can be made that will be understood by those skilled in the art within the scope of the present invention. Furthermore, any system or apparatus that combines the separate features included in each embodiment in any way is also included in the scope of the present invention.

[0048] Furthermore, the present invention may be applied to a system composed of multiple devices or to a single device. Moreover, the present invention is also applicable when an information processing program that realizes the functions of the embodiment is supplied to a system or device and executed by a built-in processor. Therefore, the technical scope of the present invention includes programs installed on a computer to realize the functions of the present invention on a computer, the medium on which the program is stored, the WWW (World Wide Web) server that allows the program to be downloaded, and the processor that executes the program. In particular, at least a non-transitory computer-readable medium containing a program that causes a computer to execute the processing steps included in the above-described embodiment is included in the technical scope of the present invention.

Claims

1. A forward-view internal image acquisition unit acquires a forward-view internal image taken by a self-propelled robot cart equipped with at least one camera capable of imaging the inside of a pipeline, while the robot cart travels inside the pipeline and the camera is pointed in the direction of travel of the self-propelled robot cart. A suspected abnormality area identification unit identifies a suspected abnormality area occurring inside the pipeline based on the forward-view internal image, A driving control unit that moves the self-propelled robot carriage to a position near the suspected abnormality area, When the self-propelled robot carriage reaches a position near the suspected abnormality area and the suspected abnormality area is no longer visible in the forward-view internal image, the camera control unit directs the camera in a direction perpendicular to the direction of travel, A side-view internal image acquisition unit acquires a side-view internal image captured by the camera, which is oriented in a direction perpendicular to the direction of travel, An abnormal state determination unit that determines the abnormal state of the suspected abnormal region based on the side view internal image, A pipeline condition determination device equipped with the following features.

2. The pipeline condition determination device according to claim 1, wherein the suspected abnormality region identification unit identifies the suspected abnormality region using a trained suspected abnormality region identification model obtained by training an artificial intelligence with forward-view internal images captured in the past, and the forward-view internal images.

3. The pipeline condition determination device according to claim 1 or 2, wherein the abnormal condition determination unit determines the abnormal condition using a trained abnormal condition determination model obtained by training artificial intelligence on previously captured side-view internal images, and the side-view internal images.

4. The pipeline condition determination device according to claim 3, wherein the abnormal condition is at least one of the following: damage to the pipeline, cracks, water infiltration, protrusion of a connecting pipe, intrusion of tree roots, and adhesion of mortar.

5. The pipeline condition determination device according to claim 1, wherein the pipeline is a sewer pipe.

6. A forward-view internal image acquisition step involves acquiring a forward-view internal image by having a self-propelled robot cart equipped with at least one camera capable of imaging the inside of a pipeline travel through the pipeline and having the camera pointed in the direction of travel of the self-propelled robot cart; A suspected abnormality region identification step, based on the forward-view internal image, identifies a suspected abnormality region occurring inside the pipeline, A driving control step that moves the self-propelled robot cart to a position near the suspected abnormality area, A camera control step is performed when the self-propelled robot cart reaches a position near the suspected abnormality area and the suspected abnormality area is no longer visible in the forward-view internal image, and the camera is directed in a direction perpendicular to the direction of travel. A side view internal image acquisition step involves acquiring a side view internal image captured by the camera oriented in a direction perpendicular to the direction of travel, An abnormal state determination step in which the abnormal state of the suspected abnormal region is determined based on the side view internal image, A method for determining the condition of a pipeline, including the following:

7. A forward-view internal image acquisition step involves acquiring a forward-view internal image by having a self-propelled robot cart equipped with at least one camera capable of imaging the inside of a pipeline travel through the pipeline and having the camera pointed in the direction of travel of the self-propelled robot cart; A suspected abnormality region identification step, based on the forward-view internal image, identifies a suspected abnormality region occurring inside the pipeline, A driving control step that moves the self-propelled robot cart to a position near the suspected abnormality area, A camera control step is performed when the self-propelled robot cart reaches a position near the suspected abnormality area and the suspected abnormality area is no longer visible in the forward-view internal image, and the camera is directed in a direction perpendicular to the direction of travel. A side view internal image acquisition step involves acquiring a side view internal image captured by the camera oriented in a direction perpendicular to the direction of travel, An abnormal state determination step in which the abnormal state of the suspected abnormal region is determined based on the side view internal image, A pipeline condition determination program that is executed by a computer.

8. A forward-view internal image acquisition unit acquires a forward-view internal image taken by a self-propelled robot cart equipped with at least one camera capable of imaging the inside of a pipeline, while the robot cart travels inside the pipeline and the camera is pointed in the direction of travel of the self-propelled robot cart. A forward-view internal image acquisition unit acquires a forward-view internal image from the first camera, which captures the direction of travel of the self-propelled robot cart, while the self-propelled robot cart is traveling inside the pipeline, using a self-propelled robot cart equipped with a first camera and a second camera capable of imaging the inside of the pipeline, A suspected abnormality area identification unit identifies a suspected abnormality area occurring inside the pipeline based on the forward-view internal image, A driving control unit that moves the self-propelled robot carriage to a position near the suspected abnormality area, A camera control unit switches from the first camera to the second camera at the moment when the self-propelled robot carriage reaches a position near the suspected abnormality area and the suspected abnormality area is no longer visible in the forward-view internal image, A side-view internal image acquisition unit acquires a side-view internal image captured by the second camera, which is oriented in a direction perpendicular to the direction of travel, An abnormal state determination unit that determines the abnormal state of the suspected abnormal region based on the side view internal image, A pipeline condition determination device equipped with the following features.

Images