JP6615065B2 - Information processing apparatus, information processing method, and program - Google Patents

Description

  The present invention relates to an information processing apparatus, an information processing method, and a program.

  With the aging of roads, bridges, facilities, etc., it is required to efficiently maintain buildings. In order to carry out the maintenance of the building, it is necessary to find a defect in the building. However, it is difficult to perform quantitative evaluation and comprehensive confirmation by visual confirmation. For this reason, automatic detection by machines is becoming widespread. For example, Patent Document 1 discloses a measurement value according to a traveling road surface position of the vehicle measured by an acceleration sensor mounted on the vehicle, and the accumulation of the measured values in each of a plurality of times of traveling for a certain road surface position. A program for causing a computer to execute a process of changing road surface deterioration detection sensitivity according to a road surface evaluation value corresponding to the certain road surface position when detecting road surface deterioration for the certain road surface position by Has been described.

JP2015-178702A

  By the way, when a plurality of defects are found in a building, it is necessary to deal with each defect systematically. Therefore, it is required to present the position and state of the defect in an easy-to-understand manner.

  An object of some aspects of the present invention is to provide an information processing apparatus, an information processing method, and a program that can easily present the state of a surface of a building or the like.

  Another object of another aspect of the present invention is to provide an information processing apparatus, an information processing method, and a program that can achieve the effects described in the embodiments described later.

In order to solve the above-described problem, one embodiment of the present invention is an image acquisition unit that acquires an image captured by an imaging device mounted on a moving body that moves along a plane and the region including the plane is captured. And for each of the images acquired by the image acquisition unit, a state determination unit that generates information in which state information indicating the state of the surface in the image is associated with position information indicating the position of the surface; The information processing apparatus includes: a display unit that associates and displays state information indicating a surface state of the position and an image including the surface at a position indicated by the position information on a map.
According to another aspect of the present invention, the information processing apparatus captures an image captured by an imaging apparatus mounted on a moving body that moves along a plane, and acquires an image in which a region including the plane is captured. And, for each of the images acquired in the first step, a second step of generating information in which state information indicating the state of the surface in the image is associated with position information indicating the position of the surface; And a third step of displaying, on the display, the state information indicating the state of the surface of the position and the image including the surface on the display in association with the position indicated by the position information on the map. Is the method.
According to another aspect of the present invention, a first step of acquiring an image captured by an imaging device mounted on a moving body that moves along a plane in a computer and an image including an area including the plane is acquired. A second step of generating, for each of the images acquired in the first step, information that associates state information indicating the state of the surface in the image with position information indicating the position of the surface; and a map A program for executing, on the position indicated by the position information, state information indicating the state of the surface at the position and an image including the surface on the display unit in association with each other. It is.

  According to one embodiment of the present invention, the state of a surface of a building or the like can be presented in an easily understandable manner.

The figure which shows the outline | summary of the malfunction analysis system 1 which concerns on the 1st Embodiment of this invention. The figure which shows the 1st example of the image which imaged the road surface image which concerns on the embodiment. The figure which shows the 2nd example of the image which imaged the road surface image which concerns on the embodiment. The figure which shows the 3rd example of the image which imaged the road surface image which concerns on the embodiment. The figure which shows the 4th example of the image which imaged the road surface image which concerns on the embodiment. The figure which shows the 5th example of the image which imaged the road surface image which concerns on the embodiment. The block diagram which shows the structure of the malfunction analysis system 1 which concerns on the same embodiment. The figure which shows the data structure of the road surface image information which concerns on the embodiment. The figure which shows the data structure of positioning information. The figure which shows the data structure of defect information. The figure which shows the data structure of ledger information. The block diagram which shows the structure of a malfunction analysis apparatus. The flowchart which shows the flow of the whole process by a malfunction analyzer. The flowchart which shows the flow of the image extraction process by a malfunction analysis apparatus. The figure which shows an example of a test | inspection image. The figure which shows an example of an area | region extraction process. The figure which shows an example of the presentation screen of defect information. The figure which shows the outline | summary of the 1st curve analysis method which concerns on the 2nd Embodiment of this invention. The figure which shows the outline | summary of the 2nd curve analysis method. The flowchart which shows the flow of the image extraction process by a malfunction analysis apparatus. The figure which shows the area | region extraction process which concerns on a modification.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
[First embodiment]
[Outline of defect analysis system 1]
A first embodiment of the present invention will be described.
FIG. 1 is a diagram showing an outline of the failure analysis system 1.
The failure analysis system 1 according to the present embodiment is a system that analyzes the state of the surface of a building. Below, the case where the malfunction analysis system 1 analyzes the visible malfunction which appeared on the surface of a building is demonstrated as an example.
A building is, for example, a road, a bridge, a facility, and the like, and includes social infrastructure.
A surface is an external or internal surface of a building. That is, the surface of a building is, for example, a road surface or a bridge of a road, an upper surface, a side surface, or a lower surface of a facility.
Visible defects are physical irregularities, color changes, and the like.

Below, the case where the malfunction which appeared on the road surface (henceforth "the road surface malfunction") is analyzed is demonstrated as an example.
Examples of road surface problems include ridges, potholes, cracks, and steps. 2 to 6 are diagrams illustrating examples of images obtained by imaging road surface problems. An image P1 shown in FIG. 2 shows an example of 轍 D1. An image P2 shown in FIG. 3 shows an example of the pothole D2. An image P3 shown in FIG. 4 shows an example of a crack D3. An image P4 shown in FIG. 5 shows an example of the step D4. The failure analysis system 1 may analyze a road surface state such as patching in addition to the road surface failure. An image P5 shown in FIG. 6 shows an example of patching D5.

Next, an outline of road surface failure analysis using the failure analysis system 1 will be described.
First, the user drives the vehicle 10 including the imaging unit 11 and travels on a road for analyzing road surface problems. The imaging unit 11 is installed in the vehicle 10 so that a road surface can be imaged. And the imaging part 11 images the road surface which changes according to driving | running | working of the vehicle 10 at any time. Hereinafter, the road surface image is referred to as a “road surface image”. In addition, the user measures the position of the vehicle 10 at any time while capturing a road surface image. Hereinafter, information (data) indicating the positioning result is referred to as “positioning information”.

  Next, the failure analysis system 1 analyzes information indicating a road surface image (hereinafter referred to as “road surface image information”) using the failure analysis artificial intelligence. The defect analysis artificial intelligence includes, for example, a multilayer perceptron (multilayer neural network). In the artificial intelligence for failure analysis, deep learning (deep learning) is performed in advance using teaching images (for example, images P1 to P5) obtained by imaging an analysis target such as a road surface failure. Arbitrary techniques and frameworks that have been used in conventional artificial intelligence may be applied to the defect analysis artificial intelligence. By deep learning, the failure analysis system 1 can detect a road surface failure reflected in a road surface image by using artificial intelligence for failure analysis. In addition, the failure analysis system 1 can specify the location where the failure exists by specifying the positioning result at the time of capturing the road surface image where the road surface failure is detected.

The failure analysis system 1 outputs the detected road surface failure and the position of the road surface failure in association with each other as a result of the analysis of the road surface image information. The failure analysis system 1 indicates, for example, the location of a road surface failure on a map and indicates the type of the road surface failure in association with each other. The analysis result may be editable by the user.
As described above, the defect analysis system 1 detects a defect reflected in an image using the artificial intelligence learned deeply. Deep learning has the characteristic that high recognition accuracy can be obtained if learning is performed with appropriate teaching information. Therefore, the failure analysis system 1 can comprehensively detect the failure of the building in the captured range.

In addition, the failure analysis system 1 does not have to include a special measurement device such as a laser irradiator, an electronic streak imaging device, or an acceleration sensor as in a conventional road surface property measurement vehicle. Therefore, the failure analysis system 1 can detect the failure of the building accurately at low cost. The failure analysis system 1 may include a laser irradiator, an electronic streak imaging device, an acceleration sensor, and the like.
The above is the description of the outline of the failure analysis system 1.

[Configuration of defect analysis system 1]
Next, the configuration of the failure analysis system 1 will be described.
FIG. 7 is a block diagram illustrating a configuration of the failure analysis system 1.
The failure analysis system 1 includes a vehicle 10, a failure analysis device 30, a failure information management device 50, a ledger information management device 70, and a map information management device 90. An imaging unit 11, a positioning unit 12, and an information terminal device 13 are mounted on the vehicle 10. The information terminal device 13, the failure analysis device 30, the failure information management device 50, the ledger information management device 70, and the map information management device 90 are each connected to the network NW and can communicate with each other.

  The vehicle 10 is a moving body that moves on a road surface so that it can be imaged. For example, the vehicle 10 is an automobile, a bicycle, a train, or the like, and is a moving body that moves on a building. Instead of a moving body that moves while contacting a building such as the vehicle 10, a moving body that does not contact the building such as a radio control helicopter or a drone may be used.

  The imaging unit 11 captures a road surface and generates road surface image information. The imaging unit 11 may capture a moving image (video) or continuously capture still images. Here, as an example, a case where the frame rate of a moving image or the imaging interval of still images is constant will be described. The road surface image information generated by the imaging unit 11 may be output to another device via a storage medium, or may be transmitted to another device via a network. The imaging unit 11 may be installed in the vehicle 10. In such a case, the imaging unit 11 may image the road surface through the windshield or rear glass of the vehicle 10. A polarization filter may be attached to the lens of the imaging unit 11 in order to suppress reflection by glass from being reflected in the road surface image.

  The positioning unit 12 performs positioning. The positioning unit 12 is, for example, a GPS (Global Positioning System) sensor. The positioning unit 12 may perform positioning using a stationary satellite type satellite navigation reinforcement system, a speed sensor such as ODB2 (On-board diagnostics 2), an acceleration sensor, or the like. The positioning unit 12 may perform positioning at a predetermined time interval, or may perform positioning in synchronization with the acquisition of the road surface image by the imaging unit 11. When the acquisition of the road surface image by the imaging unit 11 is not synchronized, the start of positioning is matched with the start of imaging. And the shift | offset | difference of the timing of imaging and the timing of positioning may specify the position corresponding to each road surface image by dividing the movement of two positioning points by the number of road surface images between them.

  The information terminal device 13 is an electronic device including a computer system such as an in-vehicle terminal such as a car navigation terminal, a smartphone, a tablet terminal, a PDA (Personal Digital Assistant) terminal, a personal computer, or a wearable terminal. The information terminal device 13 receives information from other devices connected to the network NW, displays the content of the received information, and outputs a sound. For example, the information terminal device 13 receives the information indicating the analysis result of the road surface problem and displays the analysis result. The information terminal device 13 may include an input unit such as a touch panel, a mechanical button, a keyboard, and a microphone. In this case, the input unit may transmit the content of the user input information received from the user to another device connected to the network NW.

  Note that the imaging unit 11, the positioning unit 12, and the information terminal device 13 may be integrated devices or separate devices. For example, a single smartphone may perform all of imaging of road surface images, positioning by GPS, and display of analysis results of road surface problems. Further, the imaging unit 11, the positioning unit 12, and the information terminal device 13 may be operated by voice input. Thereby, even when the vehicle 10 is traveling, the driver of the vehicle 10 can operate various devices by one person. In addition, the imaging unit 11, the positioning unit 12, and the information terminal device 13 may be remotely operated via the network NW or may be operated via short-range wireless communication such as infrared rays.

  The failure analysis device 30 is a device that analyzes a road surface failure from a road surface image. The defect information management device 50 is an electronic device including a computer system such as a personal computer or a server device. The defect analysis apparatus 30 is equipped with defect analysis artificial intelligence.

The defect information management device 50 is a device that manages defect information. Here, “information management” means that information is newly written, edited, deleted, read, received, or transmitted. The defect information management device 50 is an electronic device including a computer system such as a server device, for example.
The failure information is information relating to road surface failure such as the content of the road surface failure and the location of the road surface failure. That is, the defect information is an example of information indicating a surface state. The failure information may describe that no road surface failure exists.

The defect information management device 50 includes a first type defect information storage unit 51 and a second type defect information storage unit 52. The first type defect information storage unit 51 stores first type defect information. The second type defect information storage unit 52 stores second type defect information.
The first type trouble information is information regarding road surface troubles that have been confirmed manually. The first type defect information is used for machine learning of artificial intelligence for defect analysis.
The second type failure information is information regarding road surface failures detected by the failure analysis artificial intelligence. That is, the second type defect information is information indicating an analysis result by the defect analysis device 30.

The ledger information management device 70 is a device that manages road ledger information. The ledger information management device 70 is an electronic device including a computer system such as a server device, for example. The ledger information management device 70 includes a ledger information storage unit 71 that stores road ledger information.
The map information management device 90 is a device that manages map information. The ledger information management device 70 is an electronic device including a computer system such as a server device, for example. The map information management device 90 includes a map information storage unit 91 that stores map information. Map information is information including the name, coordinates, address, range, etc. of a building, and is information used for generating a map.
The above is the description of the configuration of the failure analysis system 1.

[Data structure of information]
Next, a data configuration of information processed by the failure analysis system 1 will be described.
First, the road surface image information will be described. Here, a case where the road surface image information is a moving image will be described as an example.
FIG. 8 is a diagram illustrating a data configuration of road surface image information.
In the example shown in FIG. 8, road surface image information includes frame number information (“frame number” in FIG. 8), frame time information (“frame time” in FIG. 8), and frame image information (“frame image” in FIG. 8). )), And these are associated with each other.
The frame number information is identification information of each frame constituting the moving image of the road surface image. The frame number information is, for example, a number assigned in ascending order to each frame from the start to the end of the moving image.

The frame time information is information indicating the timing for displaying each frame when a moving image is reproduced.
The frame image information is information indicating an image of each frame. The frame image may be encoded.
The above is the description of the data configuration of the road surface image information.

Next, positioning information will be described.
FIG. 9 is a diagram illustrating a data structure of the positioning information.
In the example illustrated in FIG. 9, the positioning information includes time stamp information (“time stamp” in FIG. 9) and positioning coordinate information (“coordinate” in FIG. 9), and is configured in association with each other.
The time stamp information is information indicating the time when positioning is performed.
The positioning coordinate information is information indicating a position specified as a result of positioning.
This completes the description of the data structure of the positioning information.

Next, the defect information will be described.
FIG. 10 is a diagram illustrating a data configuration of defect information.
In the example illustrated in FIG. 10, the defect information includes road surface defect ID (“road surface defect ID” in FIG. 10), address information (“address” in FIG. 10), and defect coordinate information (“coordinate” in FIG. 10). , Road surface failure type information (“road surface failure type” in FIG. 10) and failure image information (“image” in FIG. 10), which are associated with each other.

The road surface failure ID (Identifier) is identification information for individually identifying the road surface failure detected by the failure analysis device 30 or confirmed manually.
The address information is information indicating an address of a place where a road surface problem exists.
The defect coordinate information is information indicating the coordinates of a place where a road surface defect exists.
The road surface failure type information is information indicating the type of road surface failure.
The defect image information is information indicating an image obtained by imaging a road surface defect.
This completes the description of the data structure of the defect information.

Next, ledger information will be described.
FIG. 11 is a diagram illustrating a data configuration of ledger information.
In the example illustrated in FIG. 11, the ledger information includes route number information (“route number” in FIG. 11), road type information (“road type” in FIG. 11), and route name information (“route name” in FIG. 11). ), Section number information ("section number" in FIG. 11), improved section information ("improved section" in FIG. 11), road surface type information ("road surface type" in FIG. 11), and full width information (figure 11). 11 “full width”) and road width information (“road width” in FIG. 11), and these are associated with each other.

The route number information is identification information for identifying a road route.
The road type information is information indicating the type of road.
The route name information is information indicating the name of a road route.
The section number information is information indicating road sections on the route.
The improvement classification information is information indicating the improvement classification of the road.
The road surface type information is information indicating the type of road route.
The full width information is information indicating the full width of the road.
The road width information is information indicating the width of the road.
This completes the description of the data structure of the ledger information.

[Configuration of Defect Analysis Device 30]
Next, the configuration of the failure analysis device 30 will be described.
FIG. 12 is a block diagram illustrating a configuration of the failure analysis apparatus 30.
In the example illustrated in FIG. 12, the failure analysis apparatus 30 includes an input unit 31, a display unit 32, an audio reproduction unit 33, a communication unit 34, a storage unit 35, and a control unit 360.
The input unit 31 receives input of various information from the user of the failure analysis device 30. The input unit 31 includes, for example, a pointing device such as a mouse and a touch pad, a keyboard, and the like.
The display unit 32 displays various information such as text and images. The display unit 32 includes, for example, an organic EL (Electro-Luminescence) display panel or a liquid crystal display panel. The analysis result of the road surface failure by the failure analysis device 30 is displayed.
The audio reproduction unit 33 reproduces audio. The audio reproduction unit 33 is, for example, a speaker, an amplifier, or the like.
The communication unit 34 transmits / receives information to / from other devices. The communication unit 34 includes, for example, a communication IC (Integrated Circuit), a communication port, and the like.
The storage unit 35 stores various information. The storage unit 35 includes, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), and the like. In addition, the storage unit 35 may include an HDD (Hard Disc Drive), an EEPROM (Electrically Erasable Programmable Read Only Memory), a flash memory, and the like. The storage unit 35 stores various programs to be executed by a CPU (Central Processing Unit, not shown) and a GPU (Graphics Processing Unit, not shown) included in the failure analysis apparatus 30, results of processing executed by the CPU and the GPU, and the like. To do. The storage unit 35 includes a learning result storage unit 351.
The learning result storage unit 351 stores the learning result of the defect analysis artificial intelligence included in the defect analysis device 30. The learning result is information indicating the state of the neural network, for example. The information indicating the network state of the neural network is, for example, information indicating the parameter value of the activation function related to each node (unit) constituting the neural network.

  The control unit 360 is realized, for example, by executing a program stored in advance in the storage unit 35 by a CPU or GPU included in the failure analysis apparatus 30. A part or all of the control unit 360 may be realized as a hardware integrated circuit such as an LSI (Large Scale Integration) or an ASIC (Application Specific Integrated Circuit). The control unit 360 includes an information acquisition unit (image acquisition unit) 361, an image conversion unit 362, an analysis unit 365, a result generation unit 368, and a result editing unit 369.

  The information acquisition unit 361 acquires various types of information necessary for analyzing road surface problems via the input unit 31 and the communication unit 34. For example, the information acquisition unit 361 reads road surface image information and positioning information from the storage medium. Moreover, the information acquisition part 361 acquires road surface image information, positioning information, and user input information from the information terminal device 13, for example. Moreover, the information acquisition part 361 acquires defect information from the defect information management apparatus 50, for example. Further, the information acquisition unit 361 acquires, for example, ledger information from the ledger information management device 70. The information acquisition unit 361 outputs the acquired various types of information to the image conversion unit 362, the analysis unit 365, and the result editing unit 369.

  The image conversion unit 362 acquires road surface image information and positioning information from the information acquisition unit 361. The image conversion unit 362 converts the acquired road surface image information. Further, the image conversion unit 362 associates each frame of the road surface image with the positioning coordinate information based on the frame time information of the road surface image information and the time stamp of the positioning information. Note that the image conversion unit 362 may convert each frame into a still image when, for example, the road surface image is a moving image encoded. The image conversion unit 362 includes an image extraction unit 363 and a region extraction unit (partial image generation unit) 364.

The image extraction unit 363 executes image extraction processing.
The image extraction process is a process of extracting an image (hereinafter referred to as “inspection image”) to be analyzed for the presence or absence of a road surface defect from road surface image information. In other words, the image extraction process is a process for specifying, extracting, extracting, or narrowing down an inspection image from a series of images captured by the imaging unit 11. The image extraction process is a process of identifying, extracting, extracting, or thinning out an image that is not analyzed for the presence or absence of road surface defects from a series of images captured by the imaging unit 11.

  The image conversion unit 362 extracts the inspection image based on the positioning information so that the temporal overlap of the imaging ranges is necessary and sufficient. For example, when the imaging interval of each frame of the road surface image information is short and the moving speed of the vehicle 10 is low, the same portion of the road surface is repeatedly imaged over a plurality of frames. Thus, if the presence or absence of a road surface failure is analyzed for each of the temporally overlapping frames, the detection failure of the road surface failure can be reduced, but the load required for the analysis increases.

  Therefore, the image extraction unit 363 extracts the inspection image based on the positioning information so that the same portion of the road surface is included at a predetermined frequency in the inspection regions of a plurality of frames. The inspection area is, for example, an area to be analyzed for the presence or absence of road surface defects in the image. In the extraction of the inspection image, the frequency with which the same portion of the road surface is included may be determined based on the positioning accuracy of the positioning unit 12 and the recognition accuracy of the defect analysis artificial intelligence. For example, when the positioning accuracy and the recognition accuracy are high, the frequency may be decreased, and when the positioning accuracy and the recognition accuracy are low, the frequency may be increased.

By extracting the inspection image in this way, the failure analysis device 30 can reduce the load required for the analysis while maintaining the recognition accuracy of the road surface failure. In addition, when the inspection images are continuously displayed, the failure analysis device 30 can display the road surface image as if it is being taken while driving the vehicle 10 at a constant distance, that is, at a constant speed. Therefore, the failure analysis device 30 can make it easier to visually confirm a road surface failure reflected in the road surface image after capturing the road surface image.
The image extraction unit 363 outputs the inspection image information extracted by the image extraction process to the region extraction unit 364.

The region extraction unit 364 acquires information on the detected image from the image extraction unit 363. The region extraction unit 364 performs region extraction processing on the detected image.
The area extraction process is a process for extracting an inspection area from an inspection image. In other words, the area extraction process is a process for specifying, extracting, extracting, narrowing down, generating, or dividing the inspection image from the inspection image. The area extraction process is a process for identifying, extracting, extracting, or thinning out an area from which no road surface failure is analyzed from the inspection image. An object other than the road surface may appear in the inspection image. For example, the inspection image may include houses on the roadside, other vehicles on the road, and the like. If a road surface failure is also analyzed for objects other than these road surfaces, an object other than the road surface may be misrecognized as a road surface failure and recognition accuracy may be reduced. In particular, such misrecognition is likely to occur when machine learning for an object other than the road surface is insufficient. Further, if a road surface failure is analyzed for objects other than these road surfaces, the load required for the analysis of the road surface failure will increase.

Therefore, in the region extraction process, a road surface region is extracted as an inspection region from the inspection image. In the area extraction process, an area outside the road surface may be excluded. In the region extraction process, a plurality of regions overlapping each other may be extracted from one image. When a plurality of areas overlap, a vertex part or a side part of a certain area is included in another area.
The area extraction unit 364 outputs information on the examination area extracted by the area extraction process to the analysis unit 365. Further, the region extraction unit 364 outputs information indicating the position of each inspection region in the inspection image to the analysis unit 365.

The analysis unit 365 is implemented as an artificial intelligence for failure analysis. The analysis unit 365 includes a learning unit 366 and a recognition unit 367.
The learning unit 366 performs machine learning using the first type defect information managed by the defect information management device 50. The learning unit 366 may perform reinforcement learning using an image in which an object other than a road surface defect that may be reflected in the road surface image is captured in addition to the first-type failure information. For example, reinforcement learning may be performed using an image of a manhole or an image showing a side groove. Thereby, since the artificial intelligence for failure analysis can identify an object other than a road surface failure, it is difficult to erroneously recognize an object other than the road surface failure as a road surface failure. Therefore, the recognition accuracy of road surface problems can be improved.

  The recognition unit (state determination unit) 367 analyzes the presence or absence of road surface defects in each inspection region based on the information on the inspection region acquired from the region extraction unit 364. That is, the recognition unit 367 determines a road surface state in each inspection region. The recognition unit 367 may determine each road surface failure detected in each inspection region as one road surface failure, or collectively determine road surface failures detected in a plurality of adjacent inspection regions as one road surface failure. May be. In addition, the recognition unit 367 may determine each of the road surface defects detected in each inspection image as one road surface failure, or collectively determine the road surface failures detected in successive inspection images as one road surface failure. May be. As described above, the recognition unit 367 may perform determination by integrating determination results of a plurality of inspection regions and a plurality of inspection images.

  Further, the recognition unit 367 can specify the position of the road surface defect by specifying the positioning information corresponding to the inspection image in which the road surface problem is detected. In addition, the recognition unit 367 can further accurately specify the position of the road surface defect by acquiring information indicating the position of the inspection region in the inspection image from the region extraction unit 364. In addition, the failure analysis device 30 is combined with road surface failure analysis results using other methods such as road surface unevenness detection results based on changes in acceleration and road surface failure analysis results by other image analysis programs. The presence or absence of may be analyzed.

  The recognition unit 367 transmits the analysis result to the defect information management device 50. As a result, the analysis result is stored in the defect information management device 50 as the second type defect information. The analysis result includes, for example, an inspection image in which a road surface failure is detected, an inspection region, a road surface failure type, a determination score (certainty factor), and the like. The analysis unit 365 refers to the determination score value, the analysis result of the road surface failure in the preceding and following road surface images, the analysis result of the road surface failure in a plurality of inspection areas of the same road surface image, etc., and specifies the degree and occurrence range of the road surface failure can do. For example, when there are a plurality of road surface failure type candidates, the analysis unit 365 may set the type having the highest determination score, or may set all of them.

  In addition, the analysis unit 365 may adopt any of the determination results that are separated in the overlapped examination region. For example, if the analysis unit 365 determines that there is “road surface failure” in one inspection region and determines that there is “no road surface failure” in the other inspection region, the analysis unit 365 performs OR processing and determines that there is “road surface failure” Alternatively, an AND process may be performed to determine “no road surface problem”. When the OR process is performed and it is determined that “the road surface is defective”, the failure analysis device 30 can prevent a detection failure of the road surface failure. In addition, when performing AND processing and determining “no road surface failure”, erroneous detection of a road surface failure can be suppressed.

  The result generation unit 368 generates presentation information such as text, images, and voices indicating the first type defect information and the second type defect information (that is, the analysis result by the analysis unit 365). The result generation unit 368 generates, for example, a moving image to which defect information is added and a moving image that reproduces inspection images in the order of frame numbers. A specific example of the presentation information screen generated by the result generation unit 368 will be described later. The result generation unit 368 presents the generated presentation information via the display unit 32 and the audio reproduction unit 33. At this time, the result generation unit 368 may generate the presentation information with reference to arbitrary information managed by the defect information management device 50, the ledger information management device 70, and the map information management device 90.

The result editing unit 369 edits defect information in accordance with an instruction from the user. For example, the result editing unit 369 may edit the second type defect information stored in the defect information management device 50 in accordance with an instruction from the user. Further, for example, the result editing unit 369 may store the second type defect information stored in the defect information management device 50 as the first type defect information in response to an instruction from the user. Thereby, the road surface fault image detected by the analysis unit 365 can be used for learning the fault artificial intelligence. Note that the result editing unit 369 may perform the above-described processing in accordance with a result output from a program for detecting other road surface problems or another program used for road surface monitoring, instead of an instruction from the user.
The above is the description of the configuration of the failure analysis device 30.

[Operation of Failure Analysis Device 30]
Next, the operation of the failure analysis device 30 will be described.
FIG. 13 is a flowchart showing an overall processing flow by the failure analysis apparatus 30.
(Step S100) The information acquisition unit 361 acquires road surface image information and positioning information. Thereafter, the control unit 360 advances the process to step S102.
(Step S <b> 102) The image conversion unit 362 performs image extraction processing and extracts an inspection image. Thereafter, the control unit 360 advances the process to step S104.

(Step S <b> 104) The image conversion unit 362 performs region extraction processing to extract an inspection region. Thereafter, the control unit 360 advances the process to step S106.
(Step S106) The analysis unit 365 analyzes a road surface defect included in each inspection region of each inspection image. The analysis unit 365 causes the defect information management device 50 to store defect information indicating the analysis result as second-type defect information. Thereafter, the control unit 360 advances the process to step S108.
(Step S108) The result generation unit 368 generates presentation information for presenting the defect information managed by the defect information management device 50 to the user. The result generation unit 368 outputs the generated presentation information to the display unit 32 and the audio reproduction unit 33. Thereafter, the control unit 360 ends the process shown in FIG.
Note that the processing in steps S102 and S104 can be omitted.
This completes the description of the overall processing flow performed by the failure analysis apparatus 30.

[Image extraction processing]
Next, the image extraction process by the defect analysis device 30 will be described.
Here, as an example, a case where a road surface image corresponding to movement of a predetermined set distance is extracted from a series of road surface images that change in accordance with the movement of the vehicle 10 will be described.
FIG. 14 is a flowchart showing a flow of image extraction processing by the failure analysis apparatus 30.
(Step S200) The image extraction unit 363 selects a frame (image) based on the frame ID. For example, the image extraction unit 363 selects the first frame when no frame is selected. In addition, when the frame has already been selected, the image extraction unit 363 selects the frame next to the currently selected frame. Thereafter, the control unit 360 advances the process to step S202.

(Step S202) The image extraction unit 363 refers to the positioning information corresponding to the currently selected frame, and calculates the movement distance from the positioning result corresponding to the previous frame. Hereinafter, this movement distance may be referred to as “distance between images”. Thereafter, the control unit 360 advances the process to step S204.
(Step S204) The image extraction unit 363 adds the calculated movement distance to the total movement distance. The total moving distance is initialized at the start of the image extraction process. Thereafter, the control unit 360 advances the process to step S206.

(Step S206) The image extracting unit 363 compares the total moving distance with a predetermined set distance. When the total moving distance is larger than the set distance (step S206; YES), the control unit 360 advances the process to step S208. When the total moving distance is smaller than the set distance (step S206; NO), the control unit 360 advances the process to step S214.

  Here, the set distance may be set, for example, according to the recognition accuracy of the road surface failure in one inspection image. For example, in the case where a road surface defect that appears not only in the vicinity but in the distance can be detected in one inspection image, the set distance may be increased to reduce the overlap of the road surface in each inspection image. In addition, when a road surface failure that appears far away cannot be detected in one inspection image, the set distance may be reduced to increase the overlap of the road surface that appears in each inspection image. Thereby, the recognition accuracy of a road surface defect can be maintained, reducing the load required for the analysis of a road surface problem.

(Step S208) The image extraction unit 363 sets the total moving distance to 0 and initializes it. Thereafter, the control unit 360 advances the process to step S210.
(Step S210) The image extraction unit 363 associates the currently selected image with the positioning information. Thereafter, the control unit 360 advances the process to step S212.
(Step S212) The image extraction unit 363 sets the selected image as an inspection image. Thereafter, the control unit 360 advances the process to step S214.

(Step S214) The image extraction unit 363 confirms the presence / absence of the next image and the presence / absence of the positioning result corresponding to the image. When the image and the positioning result exist (step S214; YES), the process proceeds to the control unit 360 and step S216. When the image and the positioning result do not exist (step S214; NO), the control unit 360 advances the process to step S216.
(Step S216) The image extraction unit 363 stores the inspection image and the positioning information corresponding to the inspection image in the storage unit 35 so that they can be referred to. Thereafter, the control unit 360 ends the process shown in FIG.
Note that the detected image may be extracted regardless of the set distance, such as an interval of 10 frames. Although omitted in the processing shown in FIG. 14, the positioning information may be corrected by speed information of the vehicle 10 or the like.
The above is the description of the image extraction process.

[Area extraction processing]
Next, the area extraction process will be described.
FIG. 15 is a diagram illustrating an example of an inspection image.
In the example illustrated in FIG. 15, the imaging unit 11 is installed so as to capture the front of the vehicle 10. The inspection image P6 imaged by the imaging unit 11 includes a road surface of a two-lane road divided by three lines. Further, the inspection image P6 includes a roadside delimited by the curb R4.

  Here, in the inspection image P <b> 6, the roadway is located below the vehicle 10, and the space above the vehicle 10 is open. Since an object close to the imaging surface of the imaging unit 11 appears large, the lower side (front side) of the inspection image P6, that is, the road surface close to the vehicle 10 is greatly reflected, and the central portion (depth side) of the inspection image P6, that is, the vehicle 10 The distant road surface appears small. That is, the road surface on the lower side of the inspection image P6 is picked up with a larger number of pixels even if it actually has the same area. Therefore, even if the road surface has the same area, the road surface failure that appears on the lower side can be recognized with higher accuracy between the lower side and the center of the inspection image P6. Further, in the imaging of the inspection image P6, even when another vehicle exists in the vicinity of the vehicle 10, since the very vicinity of the vehicle 10 is imaged below the inspection image P6, the central portion The road surface will be reflected more reliably. Further, when the vehicle 10 makes a right or left turn, the amount of change in the imaging range is smaller on the lower side than the central portion of the inspection image P6. Therefore, when the vehicle 10 makes a right or left turn, a portion that is not analyzed can occur in the central portion of the inspection image P6. Further, since the vehicle 10 basically travels in the vicinity of the center of the lane, when the imaging unit 11 is set to capture the traveling direction of the vehicle 10, in the lateral direction of the inspection image P6, in particular, Roadsides and shoulders other than the road surface are easily reflected on the edge.

FIG. 16 is a diagram illustrating an example of region extraction processing.
An inspection image P7 illustrated in FIG. 16 is an image captured in the same manner as the inspection image P6 illustrated in FIG. Regions A1 to A10 illustrated in FIG. 16 indicate inspection regions set in the inspection image P7, respectively. By setting the inspection areas A1 to A10 in this way, the inspection areas A1 to A10 are less likely to include objects other than the road surface. Thereby, since it is less likely that an object other than a road surface failure is erroneously recognized as a road surface failure, the failure analysis apparatus 30 can improve the recognition accuracy of the road surface failure. Moreover, the position in the image of a road surface defect can be specified. Further, even when a plurality of road surface defects are reflected in the inspection image P7, each inspection region A1 to A10 is likely to include only individual road surface defects. As a result, the failure analysis device 30 can accurately recognize the type of individual road surface failure.

In addition, as described above, the road surface defects appearing on the lower side can be recognized with higher accuracy at the lower side and the central portion of the inspection image P7. Therefore, more inspection regions are set below the center portion in the vertical direction of the inspection image P7. Further, as described above, in the vertical direction of the inspection image P7, the road surface is shown below the center side. As described above, in the vertical direction of the inspection image P7, the change in the imaging range when turning right or left is smaller in the lower side than in the central side. Accordingly, by setting more inspection areas on the lower side, road surface problems can be recognized with high accuracy. Further, as described above, in the lateral direction of the inspection image P7, roadsides and the like other than the road surface are likely to appear in the edge of the image. Therefore, in the lateral direction of the central portion of the inspection image P7, more inspection regions are set near the center than the end portions. Moreover, inspection area | region A1-A10 is set so that the part may mutually overlap. Thereby, even if it is a case where it is contained in the boundary and edge part of an inspection area with a road surface defect, the road surface defect can be included in the vicinity of the center in the inspection area set overlapping the inspection area. Therefore, the failure analysis device 30 can suppress the detection failure of the road surface failure and improve the recognition accuracy.
The above is the description of the region extraction process.

[Presentation of defect information]
Next, presentation of defect information will be described.
The defect information may be presented by the defect analysis device 30 or the information terminal device 13.
FIG. 17 is a diagram illustrating an example of a defect information presentation screen.
In the example shown in FIG. 17, the screen O1 includes a plurality of regions O2 to O4. The screen O1 is converted into a web page, for example, and can be referred from a web browser of an arbitrary terminal.
The area O2 is an area for presenting an image displaying a marker O21 indicating the position of the vehicle 10, a marker O22 indicating the position of the road surface defect, a position where the road surface image is acquired, that is, the travel route O23 of the vehicle 10 on a map. . The marker O21, the scale of the map, and the map range of the vehicle 10 can be changed according to the operation by the user. The range of the map may be determined according to the position of the marker O21 of the vehicle 10, the position of the marker O22 of road surface malfunction, and the travel route O23 of the vehicle 10.

  Further, the road surface failure markers O22 may be grouped according to the scale of the map and the density of road surface failures. For example, the failure analysis apparatus 30 may combine road surface failures detected from a plurality of inspection regions of one inspection image, road surface failures detected from a plurality of consecutive inspection images, and the like into one marker O22. The collected markers O22 may be individually confirmed according to the selection from the user. Further, the road surface failure marker O22 has different display modes (picture, color, shape, size, transparency, etc.) depending on the type and degree of road surface failure, the occurrence range, the first type failure information or the second type failure information, and the like. ).

The region O3 is a region for displaying a road surface image. In the region O3, the inspection images extracted by the image extraction process are continuously displayed. In the image extraction process, when the frequency of overlap between images is constant, the moving image reproduced in the region O3 is expressed as if it was captured at a constant traveling speed. Therefore, the user can efficiently confirm road surface problems.
The region O4 is a region for displaying a list of road image frames including detected road surface defects. In the area O4, an inspection area O41 in which a road surface failure is detected is displayed in each frame.

  The displays of the regions O2 to O4 may be linked to each other. For example, a road surface image captured at the position O21 of the vehicle 10 in the region O2 may be displayed in the region O3. Further, a road surface image including a road surface defect located at a predetermined distance from the position O21 of the vehicle 10 may be displayed in the region O4. For example, in the region O2, the display of the region O3 and the display of the region O4 may be switched in accordance with the change of the position of the marker O21 of the vehicle 10.

  In addition, any information other than the above may be displayed on the presentation screen O1. For example, when the road surface failure marker O22 is selected, the failure analysis apparatus 30 may display various information such as a position, a road surface failure type, an imaging time, a route number, a road construction history, and the like regarding the road surface failure. . In addition, the failure analysis device 30 may display a numerical value such as the total number of road surface failures and the average of each road surface failure for each travel distance on the presentation screen O1. In addition, the failure analysis device 30 is provided with an imaging time, weather, road surface failure analysis results using other methods (road surface unevenness detection results based on acceleration changes, road surface failure analysis results from other image analysis programs), etc. May be displayed.

Moreover, the information terminal device 13 and the failure analysis device 30 may accept correction of the failure information by the user via the presentation screen O1. For example, when the road surface failure marker O22 is selected by the user, the deletion of the marker O22 or the change of the road surface failure type may be accepted. Further, when the road surface image displayed in the region O3 and the region in the road surface image are selected, the failure analysis apparatus 30 selects the selected region and the road surface image, and positioning information corresponding to the road surface image. The defect information may be generated based on the above. Then, the generated defect information may be stored in the defect information management apparatus 50 as the first type defect information.
The above is an explanation of presentation of defect information.

[Summary of First Embodiment]
As described above, the failure analysis apparatus 30 performs learning that performs deep learning on an image obtained by imaging a surface (for example, a road surface) based on teaching data (for example, first-type failure information) indicating the state of the surface. And an information acquisition unit 361 that acquires an image in which a region including a surface is captured (for example, a road surface image) and is associated with position information (for example, positioning information) indicating the captured position. And a recognizing unit 367 for determining the state of the surface in the image acquired by the information acquiring unit 361 based on the learning result of the learning unit 366.
Thereby, the malfunction analysis apparatus 30 can comprehensively analyze the state of each place about the imaged surface.

Further, in the defect analysis device 30, the recognition unit 367 determines the state of the surface by integrating the determination results of the surface state in each of the plurality of partial images output from one image.
Thereby, the failure analysis apparatus 30 determines the state of each place on the surface with reference to the surrounding state. Therefore, the failure analysis apparatus 30 can improve the accuracy of determining the surface state.

Further, in the defect analysis device 30, the recognition unit 367 integrates the determination results of the surface state in each of a plurality of subsequently captured images acquired by the information acquisition unit 361, and determines the state of the surface. judge.
Thereby, the failure analysis apparatus 30 determines the state of each place on the surface with reference to the surrounding state. Therefore, the failure analysis apparatus 30 can improve the accuracy of determining the surface state.

In the failure analysis device 30, for example, teaching data (for example, first type failure information) is data obtained by determining the determination result by the recognition unit 367 based on the input from the user or the determination result by another device. It is.
Thereby, when the user confirms the validity of the determination result of the defect analysis device 30, the image used for the determination can be used for the deep learning. For example, even when the determination result is incorrect, the defect analysis device 30 can perform re-learning, so that a more correct determination result can be displayed. Therefore, the failure analysis apparatus 30 can improve the accuracy of determining the surface state.

In addition, the failure analysis apparatus 30 continuously captures images with the imaging unit 11 mounted on a moving body (for example, the vehicle 10) that moves along a plane (for example, a road surface), and captures an area including the plane. Based on the information acquisition unit 361 that acquires the movement information (for example, positioning information) of the moving body, the first image is thinned out from the continuously captured image (for example, road surface image), thereby An image extraction unit 363 that extracts two images (for example, inspection images), and a recognition unit 367 that determines a state of a surface in the second image for each of the second images.
Thereby, the failure analysis apparatus 30 adjusts the amount of the image for determining the surface state according to the movement of the moving body. Therefore, the failure analysis apparatus 30 can reduce the load required for the determination while maintaining the accuracy of determining the surface state.

Further, in the failure analysis apparatus 30, the image extraction unit 363 extracts the second image (for example, an inspection image) based on the moving distance with respect to time of the moving body (for example, the vehicle 10).
Thereby, the malfunction analysis apparatus 30 adjusts the amount of the image for determining the surface state according to the moving speed of the moving body. Therefore, the failure analysis apparatus 30 can reduce the load required for the determination while maintaining the accuracy of determining the surface state.

In addition, the failure analysis apparatus 30 obtains an image in which an image is captured continuously by the imaging unit 11 mounted on a moving body (vehicle 10) that moves along a surface (for example, a road surface) and an area including the surface is captured. Information acquisition unit 361, a region extraction unit 364 that outputs a plurality of partial images that are part of the image acquired by the information acquisition unit 361, and a partial image that is output by the region extraction unit 364. A recognizing unit 367 for determining the state of the surface.
Thereby, since the defect analysis apparatus 30 determines the state of the surface from a part of the image, when an element that decreases the determination accuracy is reflected in the image, the defect analysis apparatus 30 can perform the determination by removing the element. Therefore, the failure analysis apparatus 30 can improve the accuracy of determining the surface state.

Further, in the failure analysis device 30, the region extraction unit 364 displays the partial image in front (for example, the lower inspection region A1 in FIG. 16) with respect to the traveling direction of the moving body (for example, the vehicle 10). More than the partial image at the back (for example, the inspection area A10 at the center in FIG. 16) is output.
As a result, the failure analysis apparatus 30 preferentially determines the state of the surface that appears on the near side with a large amount of information in the image. In addition, since the vicinity of the moving object is captured on the near side of the image, it is difficult to capture an object other than the surface. In addition, on the near side of the image, the amount of change in the imaging range when the moving direction of the moving body changes is small. Therefore, the failure analysis device 30 can improve the determination accuracy of the surface state and reduce the load required for the determination.

In the defect analysis apparatus 30, the region extraction unit 364 divides an image (for example, an inspection image), and divides the divided first partial image (for example, the inspection region A1 in FIG. 16) and the first partial image. A second partial image (for example, region A5 in FIG. 16) including the vertex portion or the side portion is output.
Thereby, the failure analysis apparatus 30 generates a plurality of overlapping partial images from one image. Therefore, the failure analysis device 30 can improve the determination accuracy of the state of the boundary surface of the partial image.

In addition, the failure analysis apparatus 30 acquires an image captured by the imaging unit 11 mounted on a moving body (for example, the vehicle 10) that moves along a plane (for example, a road surface) and an area including the plane is captured. Information acquisition unit 361 that performs state information (for example, defect information) that indicates the state of the surface in the image, and position information that indicates the position of the surface (for example, positioning) Information), a display that displays the state information indicating the surface state of the position and the image including the surface in association with the position indicated by the position information on the map. Unit 32.
Thus, the user can immediately grasp which surface at which position is in what state by referring to the map. That is, the failure analysis device 30 can present the surface state in an easy-to-understand manner.

In the failure analysis apparatus 30, the display unit 32 is a surface (for example, road surface) to which the position information (for example, failure coordinate information) belongs within a predetermined range (for example, within a predetermined distance), and the state For a plurality of surfaces having the same information (for example, failure information) (for example, there is a road surface failure), the state information is displayed in association with a representative position representing the plurality of surfaces.
Thereby, even if it is a case where a plurality of state information is crowded on the map, the defect analysis device 30 can present the surface state in an easy-to-understand manner because the representative position is indicated.
The above is the description of the first embodiment.

[Second Embodiment]
A second embodiment will be described. Here, about the structure similar to each embodiment mentioned above, the same code | symbol is attached | subjected and description is used.
[Outline of defect analysis system 1A]
A failure analysis system 1A (not shown) according to the present embodiment has the same configuration as the failure analysis system 1 according to the first embodiment. However, the failure analysis system 1A is different in that it performs a process of detecting a road curve in the image extraction process. On the curve, the moving direction of the vehicle changes. Even if the moving speed of the vehicle 10 is constant on the curve, the change in the imaging range, particularly on the far side of the road surface image, is larger than the straight line. Therefore, the movement distance between images is corrected according to the degree of the curve. Thereby, it is possible to improve the analysis accuracy of road surface problems and reduce the processing load required for the analysis.

[Configuration of defect analysis system 1A]
The failure analysis system 1A includes a failure analysis device 30A (not shown) instead of the failure analysis device 30 included in the failure analysis system 1. The defect analysis apparatus 30A includes an image extraction unit 363A (not shown) instead of the image extraction unit 363 included in the defect analysis apparatus 30.
The image extraction unit 363A performs image extraction processing in the same manner as the image extraction unit 363. However, the image extracting unit 363A is different in that the moving distance between images is corrected according to the road curve. The image extraction unit 363A corrects the moving distance between images to be larger as the degree of the curve is larger (that is, as the curve is steeper), and as the degree of the curve is smaller (that is, the curve is gentler). The correction is made so that the moving distance between the images becomes small. That is, the smaller the degree of the curve, the thinner the road image, and the smaller the degree of the curve, the more the road image is thinned out. As a result, more images are extracted as the degree of the curve is larger, and fewer images are extracted as the degree of the curve is smaller.

Here, two types of curve analysis methods will be described.
First, the first curve analysis method will be described.
FIG. 18 is a diagram showing an outline of the first curve analysis method.
In the example shown in FIG. 18, there are eight positioning points m1 to m8 on the road R10. The road R10 is curved over the positions m4 to m7.
In the first curve analysis method, the inclination degree is measured from three consecutive positioning information. For example, when analyzing a curve at the positioning point m5, a moving direction v4 from the positioning point m4 to the positioning point m5 and a moving direction v5 from the positioning point m5 to the positioning point m6 are calculated. Then, the angle θ formed by the two movement directions v4 and v5 is calculated. Accordingly, the image extraction unit 363A can calculate the angle θ indicating the degree of the curve.

Next, the second curve analysis method will be described.
FIG. 19 is a diagram showing an outline of the second curve analysis method.
In the example shown in FIG. 19, as in the example shown in FIG. 18, there are eight positioning points m1 to m8 on the road R10.
In the second curve analysis method, the degree of curve is calculated by comparing the total distance between positions measured within a predetermined period with the distance between positions measured at the beginning and end of the predetermined period. For example, when the positioning points specified within a predetermined period from the measurement start of the positioning point m2 are the positioning points m3 to m7, the image extraction unit 363 determines the positioning points m2 to m3, m3 to m4, m4 to m5, m5. The total sum L1 of the distances between m6 and m6 to m7 is calculated. Further, the image extraction unit 363A calculates a linear distance L2 between the positioning points m2 to m7. The image extraction unit 363A can specify the degree of the curve by comparing the distance L1 and the distance L2. For example, the shorter the distance L2 compared to the distance L1, the greater the degree of curve. If the distance L1 and the distance L2 are approximately the same, the degree of the curve is small.

In the first curve analysis method described above, it is possible to determine a right turn and a left turn.
In the second curve analysis method described above, only calculation of distance and comparison of distance are performed, so that the load required for processing can be reduced.
The above is the description of the configuration of the failure analysis system 1A.

[Operation of Failure Analysis Device 30A]
Next, the operation of the failure analysis apparatus 30A will be described. Here, the operation in the image extraction process will be described.
FIG. 20 is a flowchart showing the flow of image extraction processing performed by the failure analysis apparatus 30A.
The processes in steps S200, S202, and S204 to S216 shown in FIG. 20 are the same as the processes shown in FIG.

(Step S203A) After the process of step S202, the image extraction unit 363A calculates the degree of the curve. Then, the image extraction unit 363A corrects the moving distance between the images according to the degree of the curve. Thereafter, the control unit 360 advances the process to step S204.
Although the case where the movement distance between images is corrected has been described here, the set distance may be corrected instead of the movement distance between images. Further, the correction of the distance may be performed by an arbitrary method. For example, a correction amount for each degree of the curve may be set in advance, and the distance may be corrected based on the correction amount, or may be corrected by a function including a parameter indicating the degree of the curve.
The above is the description of the operation of the failure analysis apparatus 30A.

[Summary of Second Embodiment]
As described above, the failure analysis apparatus 30A extracts the second image (for example, an inspection image) based on the amount of change (for example, the degree of the curve) in the moving direction of the moving body (for example, the vehicle 10).
Thereby, the malfunction analysis device 30A changes the extraction amount of the second image in accordance with, for example, the change amount of the moving direction of the moving body. That is, the extraction amount of the second image is changed in accordance with the change in the imaging range of the image. Therefore, even when the moving direction of the moving body is not constant, the second image necessary and sufficient for determining the surface state can be extracted.

In addition, when the amount of change in the moving direction (for example, the degree of the curve) of the moving body (for example, the vehicle 10) is large, more second images ( For example, an inspection image) is extracted.
Thereby, even if it is a case where the moving direction of a moving body is not constant, malfunction analysis apparatus 30A can extract the 2nd image sufficient and sufficient for determination of the state of a surface.
The above is the description of the second embodiment.

[Modification]
The embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to the above-described embodiment, and includes a design and the like within a scope not departing from the gist of the present invention. For example, the configurations described in the first and second embodiments described above can be arbitrarily combined. In addition, for example, each configuration described in the first and second embodiments described above can be omitted if it is not necessary to exhibit a specific function. Further, for example, each configuration described in the first and second embodiments described above can be arbitrarily separated and provided in a separate device.

  Note that the information terminal device 13 may be carried by the user without being mounted on the vehicle 10. Then, the information terminal device 13 may generate defect information related to road surface defects discovered by the user inside and outside the vehicle 10. For example, a still image may be captured in response to a voice input “crack” by the user, and defect information in which “crack” is associated with the captured still image as a road surface defect type may be generated. In this case, the defect information generated by the information terminal device 13 may be stored in the defect information management device 50 as the first type defect information. Alternatively, flag information may be associated with the road surface image being captured in response to a voice input “crack” by the user. This flag information is information indicating the confirmation result of road surface problems by the user. The failure analysis device 30 is thickened by preferentially extracting the road surface image associated with the flag information as a detected image in the image extraction process or increasing the number of inspection areas to be extracted in the area extraction process. You may make it analyze. As a result, the failure analysis systems 1 and 1A can prevent a road surface failure from being detected and improve the recognition accuracy of the road surface failure.

  Note that the imaging unit 11 and the positioning unit 12 may be equipped with a function that supports imaging and positioning. For example, it may be notified that imaging or positioning can be performed when the installation environment of the imaging unit 11 is prepared or GPS radio waves can be received and positioning becomes possible.

  The information terminal device 13 may present the defect information to the user in synchronization with the movement of the own device. For example, the marker O21 of the vehicle 10 shown in FIG. 17 may be synchronized with the position of the own device. Further, when the own apparatus is located in the vicinity of the marker O22, the user may be notified that a road surface problem exists in the vicinity. Thereby, the user can confirm a road surface problem located in the vicinity of the user. For example, the user can easily check road surface problems detected in the past by carrying the information terminal device 13 and driving the vehicle. Therefore, the failure analysis systems 1 and 1A can easily reconfirm the position and progress of the road surface failure, and can notify the danger of the road surface failure.

As described above, the information terminal device 13 determines the surface (for example, the road surface) based on the position of the moving body (for example, a vehicle different from that at the time of capturing the road surface image) based on the output from the failure analysis device 30. Display the image that contains it.
Thereby, since the information terminal device 13 presents an image of a surface in the vicinity of the moving body, for example, the state of the surface can be presented in an easy-to-understand manner to a user who is moving on the moving body.

Further, the information terminal device 13 is based on the position of the moving body (for example, a vehicle different from that at the time of capturing the road surface image) and the position information (for example, positioning information) based on the output from the failure analysis device 30. Status information corresponding to the position information is displayed.
Thereby, since the information terminal device 13 presents the state of the surface in the vicinity of the moving body, for example, the state of the surface can be easily presented to the user who is moving on the moving body.

  Note that the defect analysis devices 30 and 30A may perform machine learning in advance so as to recognize objects and defects other than those described above. For example, the failure analysis device 30 recognizes manholes, tunnel wall damage, road fallen objects, road oil stains, guardrail damage, telephone pole damage, road graffiti, road signs, lane markings, snow, flooding, gutter breakage, etc. You may make it do. Moreover, you may make it recognize the degree about the item to recognize.

  The failure analysis devices 30 and 30A may determine the road surface state by integrating road surface images captured by the plurality of imaging units 11. For example, a plurality of vehicles 10 run in parallel on a road, and the imaging unit 11 mounted on each vehicle captures a road surface image. Moreover, the positioning part 12 mounted in each vehicle 10 performs positioning, respectively. The failure analysis devices 30 and 30A rearrange and reconstruct the plurality of road surface images thus imaged based on the imaging time of each frame, for example. Then, the failure analysis devices 3030 and 30A may determine the road surface state for the reconstructed road surface image.

The defect analysis devices 30 and 30A may perform a process of excluding (thinning out) areas other than the inspection area in the area extraction process.
FIG. 21 is a diagram illustrating another example of the region extraction processing.
In the example shown in FIG. 21, the area A21 is thinned out from the inspection image P8, and the remaining trapezoidal area is set as the inspection area. The area A21 may be determined in advance according to how the road surface is reflected in the captured image. As described above, the defect analysis devices 30 and 30A may define a region that is not an inspection region.

  In the above-described embodiment, the case of extracting a plurality of inspection regions having the same size has been described in the region extraction processing. However, the present invention is not limited to this. For example, in the road surface image, the inspection area may be set small for the depth side, that is, a distant part, and the inspection area may be set large for the near side, that is, a vicinity part. For example, in the example shown in FIG. 16, the size of the region A10 may be set smaller than the size of the regions A1 to A4. Thereby, on the depth side of the road surface image, it is possible to prevent a plurality of road surface defects from being included in one detection region or an object other than a road surface failure from being included in the detection region.

  In the above-described embodiment, the case of extracting a plurality of inspection regions in the region extraction process has been described. However, the present invention is not limited to this. Each inspection area may be extracted so as not to overlap. Further, the defect analysis devices 30 and 30A may extract the inspection region so as to cover all the portions of the inspection image.

  In the area extraction process, the inspection area may not be fixed. For example, the defect analysis devices 30 and 30A may change the position and number of inspection regions in accordance with a change in the movement direction. The defect analysis devices 30 and 30A set, for example, more inspection areas on the right side of the inspection image in the case of a right turn, and set more inspection areas on the left side of the inspection image in the case of a left turn. Also good. In addition, the defect analysis devices 30 and 30A may change the position and number of inspection regions according to the amount of change in the movement direction, for example. For example, when the degree of the curve is large, more inspection regions may be set on the front side of the inspection image.

  In addition, the failure analysis devices 30 and 30A may output an analysis result indicating that the inspection area cannot be analyzed. For example, when the road surface is not reflected in the inspection area, the inspection area is unclear due to the influence of shadows, there is snow, or there is flooding, the failure analysis apparatuses 30 and 30A are incapable of analysis. The analysis result may be output together with the reason.

  In addition, although embodiment mentioned above demonstrated the aspect which detects a road surface malfunction using the artificial intelligence for malfunction analysis, it is not restricted to this. For example, the failure analysis apparatuses 30 and 30A may extract an image feature amount and analyze a road surface failure. In addition, the failure analysis devices 30 and 30A may analyze the road surface failure using a technique such as a support vector machine or clustering, for example.

In addition, the presentation aspect of defect information is not restricted to what was mentioned above. The failure analysis devices 30 and 30A may analyze, for example, road surface images taken at different times and present only locations where road surface failures have increased.
Note that the analysis range of a series of road surface images captured at a time may be determined by input from the user. For example, the defect analysis devices 30 and 30A may accept a range of frames to be analyzed by specifying a time or by specifying a location. When receiving the designation of the place, the failure analysis apparatuses 30 and 30A may determine the analysis range with reference to the coordinates of the designated place and the positioning information associated with the road surface image.

  The positioning information may be improved in accuracy by any method. For example, the defect analysis devices 30 and 30A can use speed information measured by GPS by the Doppler method or speed information obtained by ODB2 or the like, so that even if there is an error in the positioning result by GPS, based on the speed information. It is possible to improve the positioning accuracy by correcting the moving distance. Further, for example, the failure analysis devices 30 and 30A may improve positioning accuracy using road information, travel route information input by the user, and the like.

Note that the imaging unit 11 may be mounted on the vehicle 10 in any manner.
The imaging unit 11 may be installed inside the vehicle or may be installed outside the vehicle. The imaging unit 11 may be installed so as to capture the front of the vehicle, or may be installed so as to capture the rear. The imaging unit 11 may be carried by the user, such as worn by the user.

  Further, a program for realizing the functions of the information terminal device 13, the failure analysis device 30, the failure information management device 50, and the map information management device 90 described above is recorded on a computer-readable recording medium and recorded on this recording medium. The processing as the information terminal device 13, the failure analysis device 30, the failure information management device 50, and the map information management device 90 may be performed by causing the computer system to read and execute the program. Here, “loading and executing a program recorded on a recording medium into a computer system” includes installing the program in the computer system. The “computer system” here includes an OS and hardware such as peripheral devices. Further, the “computer system” may include a plurality of computer devices connected via a network including a communication line such as the Internet, WAN, LAN, and dedicated line. The “computer-readable recording medium” refers to a storage device such as a flexible medium, a magneto-optical disk, a portable medium such as a ROM and a CD-ROM, and a hard disk incorporated in a computer system. As described above, the recording medium storing the program may be a non-transitory recording medium such as a CD-ROM. The recording medium also includes a recording medium provided inside or outside that is accessible from the distribution server in order to distribute the program. The code of the program stored in the recording medium of the distribution server may be different from the code of the program that can be executed by the terminal device. That is, the format stored in the distribution server is not limited as long as it can be downloaded from the distribution server and installed in a form that can be executed by the terminal device. Note that the program may be divided into a plurality of parts, downloaded at different timings, and combined in the terminal device, or the distribution server that distributes each of the divided programs may be different. Furthermore, the “computer-readable recording medium” holds a program for a certain period of time, such as a volatile memory (RAM) inside a computer system that becomes a server or a client when the program is transmitted via a network. Including things. The program may be for realizing a part of the functions described above. Furthermore, what can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, and what is called a difference file (difference program) may be sufficient.

DESCRIPTION OF SYMBOLS 1, 1A ... Defect analysis system, 10 ... Vehicle, 11 ... Imaging part, 12 ... Positioning part, 13 ... Information terminal device, 30, 30A ... Defect analysis apparatus, 31 ... Input part, 32 ... Display part, 33 ... Sound reproduction 34, communication unit, 35 ... storage unit, 351 ... learning result storage unit, 360 ... control unit, 361 ... information acquisition unit, 362 ... image conversion unit, 363, 363A ... image extraction unit, 364 ... region extraction unit, 365 ... analyzing unit, 366 ... learning unit, 367 ... recognizing unit, 368 ... result generating unit, 369 ... result editing unit, 50 ... defect information management device, 51 ... first type defect information storage unit, 52 ... second type defect Information storage unit, 70 ... ledger information management device, 71 ... ledger information storage unit, 90 ... map information management device, 91 ... map information storage unit

Claims (6)

By the imaging device mounted on the moving body that moves along the front surface of a building, an image acquisition unit that area including the table surface to obtain an image captured,
For each of the images acquired the image acquisition unit, and status information indicating the status of the table surface in the image, and position information indicating a position of the table surface, and a state determining unit that generates information that associates ,
On the map, the position where the position information indicates, and status information indicating the status of the table surface of the position, and a display unit for displaying in association with an image including the table surface,
Equipped with a,
When the position on the map is specified, the display unit,
In the first area, a moving image linked to a position on the map is displayed based on the image acquired by the image acquisition unit,
In the second region, a plurality of images based on the frames in the moving image displayed in the first region and having the surface defect detected are displayed side by side.
Information processing device. The display unit displays an image in which at least a part of a region other than the surface is excluded in the frame as an image based on the frame;
The information processing apparatus according to claim 1. The display unit displays the moving image with the frame adjusted so that the same part of the surface is included at a predetermined frequency .
The information processing apparatus according to claim 1 or 2. By the imaging device mounted on the moving body that moves along the front surface of a building, an image acquisition unit that area including the table surface to obtain an image captured,
Based on a learned model that is a result of machine learning using an image and state information indicating the state of the surface of a building in the image, for each of the images acquired by the image acquisition unit, the image in the image determines the state of the front surface, and a state determining unit that generates the status information indicating the status, the information that associates the position information indicating the position of the table surface,
On the map, the position where the position information indicates, and status information indicating the status of the table surface of the position, and a display unit for displaying in association with an image including the table surface,
A learning unit that performs the machine learning using the state information changed with the image when the user inputs a change about the state information associated with the image displayed on the display unit;
An information processing system comprising: Information processing device
By the imaging device mounted on the moving body that moves along the front surface of a building, comprising: a first step of a region including the table surface to obtain an image captured,
For each of images obtained in the first step, a second step of generating a status information indicating the status of the table surface in the image, information that associates the position information indicating a position of the table surface When,
On the map, the position where the position information indicates, and status information indicating the status of the table surface of the position, and a third step of displaying on the display unit in association with the image, the including the table surface,
When the position on the map is designated, in the first area, a moving image linked to the position on the map and based on the image acquired in the first step is displayed, and in the second area, A fourth step of displaying a plurality of images based on the frames in the moving image displayed in the first region, the frames having the surface defect detected;
An information processing method including: On the computer,
By the imaging device mounted on the moving body that moves along the front surface of a building, comprising: a first step of a region including the table surface to obtain an image captured,
For each of images obtained in the first step, a second step of generating a status information indicating the status of the table surface in the image, information that associates the position information indicating a position of the table surface When,
On the map, the position where the position information indicates, and status information indicating the status of the table surface of the position, and a third step of displaying on the display unit in association with the image, the including the table surface,
When the position on the map is designated, in the first area, a moving image linked to the position on the map and based on the image acquired in the first step is displayed, and in the second area, A fourth step of displaying a plurality of images based on the frames in the moving image displayed in the first region, the frames having the surface defect detected;
A program for running