JP2019196680A - Pavement information gathering inspection system, pavement information gathering inspection method, and program - Google Patents

Abstract

To construct a road surface inspection technique which can be introduced with inexpensive capital investment, is resistant to errors, and enables highly accurate data analysis to facilitate road management.SOLUTION: A pavement information recorder 10 acquires flatness data measured at the time of traveling by an acceleration sensor, an angular velocity sensor, or both while measuring latitude and longitude information while a vehicle 2 is driven. Road surface images being still images or moving images of the road surface ahead or behind are imaged with a camera while traveling. A flatness analyzer 31 estimates an IRI at each point corresponding to the latitude and longitude information using the flatness data. An image analysis device 32 detects cracks on the road surface at each point corresponding to the latitude and longitude information by analyzing the road surface images. Points on a map which can be referenced are displayed on a terminal 51 by a web server 41.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a system that can collect and analyze road pavement conditions and use it for inspection, an inspection method thereof, and a program.

  The road infrastructure that was intensively developed during the period of high economic growth is currently concerned about rapid aging. However, maintenance and repair costs are declining due to a shortage of financial resources in the national and local governments, and inspection and maintenance must be carried out with limited financial resources. For important trunk lines, regular inspections using road surface property measuring vehicles are preferentially implemented.

  As a technology for inspecting road surface properties, development of a technology for measuring cracks, rutting, IRI (International Roughness Index), etc. by attaching a laser scanner, a camera, etc. to a vehicle is progressing. In addition, a technique for grasping IRI by measuring acceleration, GPS information, and moving image information of a smartphone and easily measuring, analyzing, and recording road surface properties has been studied.

  As for the soundness of the roadbed below the road surface, a dynamic deflection measuring device (MWD: Moving Wheel Deflectometer) has been developed that measures the amount of pavement deflection while driving a vehicle without road regulation.

  As described in Non-Patent Document 1, the pavement management for these road surfaces and roadbeds has been studied for public operation.

Ministry of Land, Infrastructure, Transport and Tourism 6th Road Technology Subcommittee (September 13, 2016) Handouts [Document 3-2] Pavement management in the future (PDF format: 807KB) http://www.mlit.go.jp/ common / 001145725.pdf

  However, with regard to residential roads and semi-trunk roads, they cover live roads and some semi-trunk roads, mainly through visual inspections during patrols by local government employees or contractors and response to reports from residents. Yes. However, most roads have not been inspected due to lack of human resources. In order to support this, there are services that display on the map a point where it is determined that there is a crack by image analysis, or display an IRI on the map.

  In addition, individual measurement data alone may not be suitable for analysis, and analysis accuracy may be insufficient. For example, in photographing, an excessive amount of light due to backlight or the like, an insufficient amount of light due to a shade or a tunnel, and a blurred image due to a sudden change in the amount of light may occur. In addition, the road surface may not be visible due to preceding vehicles, fallen leaves, dumped objects, or other obstacles, and incidental objects around the road such as curbs and gratings may be reflected in the analysis target area. Although it is desirable, there are cases where it is forced to operate not straight ahead due to road conditions or traffic restrictions, and there are cases where the road surface is not visible when the road is narrow or turning right or left. Furthermore, the image may be blurred due to camera shake caused by short-term rain or watering, wetness of the ground due to rain on the previous day, road surface conditions, traffic restrictions, or danger avoidance. In any case, it is inevitable that the image is inappropriate and erroneous detection, detection omission, and calculation error associated therewith occur. In any case, even if the accuracy of machine learning is improved, it is difficult to completely avoid problems caused by the environment for taking pictures.

  On the other hand, IRI is a value calculated from the inclination and acceleration measured using a smartphone sensor, etc., so the value is high even when there is a step or unevenness in a normal state such as a connection part with a manhole or bridge. turn into. It is difficult to determine the location where a defect has occurred and the location where it is not based only on the IRI value displayed on the map.

  These problems can be compensated with human resources by using an expensive road surface property measuring vehicle for main roads. However, the human resources of the local government are limited, and it is difficult to cover all of the overwhelmingly long life roads. In addition, it is impossible in terms of budget to repair all the parts where cracks are detected or IRI is bad. Of the places where cracks are detected or where the IRI is bad, the place where repair is highly urgent is prioritized, and the place where the possibility of an accident is low has to be postponed. For example, even if there are cracks or irregularities on the roadway, it is actually necessary to make a decision to postpone the roadside belt or sidewalk if it is a well-developed part.

  Therefore, the present invention combines the established road surface inspection technology, can efficiently grasp the road surface condition even in an environment where human resources are limited, and can efficiently find a place where repair is necessary. Thus, it aims at facilitating management until inspection and repair of information in general roads including a life road.

In the driving environment mounted on the vehicle, the present invention
Each acceleration acquisition means for acquiring flatness data for calculating IRI, which is measured during traveling by an acceleration sensor, an angular velocity sensor, or both;
Road surface image acquisition means for capturing a road surface image that is a still image or a moving image including a road surface on the front or rear side while traveling by a camera;
Position information acquisition means for continuously acquiring latitude and longitude information during traveling by the position information positioning device;
Position correspondence recording means for recording the flatness data and the road surface image so as to be associated with latitude and longitude information of the acquired point;
A pavement information recording device composed of one or a plurality of devices,
A flatness analyzer for executing IRI estimation means for estimating IRI at each point corresponding to the latitude and longitude information from the flatness data;
An image analyzer for executing crack detection means for detecting cracks on the road surface at each point corresponding to the latitude and longitude information by analyzing the road surface image;
A web that can execute pavement information visualization means that receives the IRI, the crack, and the road surface image from the flatness analysis device and the image analysis device and displays them in a referable manner from a point on the map in response to a request from the terminal. Server,
The above problem was solved by the pavement information collection and inspection system having

  That is, as the pavement information recording device, the flatness data is acquired by a smartphone having an acceleration sensor, an angular velocity sensor, and the like, and the road surface image is acquired by a video camera or the like. Any information is recorded while being associated with latitude / longitude information so that it can be analyzed, and even if an error is included in the measurement of the flatness data or the road surface image, it is displayed on the terminal by the web server. When IRI and cracks are confirmed on a map, they can be mutually confirmed and the road surface image can also be referred to. By examining the IRI and cracks on the map on the screen to narrow down the candidates for the places where repair is necessary to some extent, and further confirming with the road surface image, it can be executed as a series of systems and methods.

Furthermore, as a pavement information collection inspection method according to the present invention,
While driving the vehicle and measuring the latitude and longitude information,
Each acceleration acquisition means for acquiring flatness data for calculating IRI, which is measured during traveling by an acceleration sensor, an angular velocity sensor, or both;
Road surface image acquisition means for capturing a road surface image that is a still image or a moving image including a road surface on the front or rear side while traveling by a camera;
Performing the steps in parallel,
IRI estimation means for estimating IRI at each point corresponding to the latitude / longitude information from the flatness data;
Crack detection means for detecting cracks on the road surface at each point corresponding to the latitude and longitude information by analyzing the road surface image,
Steps to perform both
And executing a pavement information visualization means for displaying the IRI, the crack, and the road surface image so that they can be referred to from a point on the map in response to a request from the terminal.

Moreover, the pavement information collection inspection service system according to the present invention is
The IRI at each point corresponding to the latitude / longitude information is estimated using flatness data measured at the time of traveling by an acceleration sensor, an angular velocity sensor, or both mounted on a vehicle that continuously measures latitude / longitude information while traveling. A flatness analyzer for executing IRI estimation means;
Using a road image that is a still image or a moving image including a road surface in front or behind the vehicle that is running by a camera mounted on the vehicle, the road surface cracks at each point corresponding to the latitude and longitude information are analyzed by the road image. An image analysis device for executing crack detection means for detecting;
A web server that executes the pavement information visualization means that receives the information of the IRI, the crack, and the road surface image at each point and displays the information on the map so that the terminal can be referred to;
Have

  The program according to the present invention is a program for causing a computer to execute as the web server.

  The flatness data is data affected by road surface unevenness obtained from an acceleration sensor, an angular velocity sensor, or both. For example, the vertical acceleration during traveling, which is an acceleration in the vertical direction directly measured during traveling, the angular velocity during acceleration / deceleration, which is an angular velocity due to acceleration / deceleration of the vehicle, and the vertical acceleration during acceleration / deceleration, which is acceleration due to acceleration / deceleration, are flat. Useful as sex data. In this case, the IRI estimating means extracts the uneven acceleration which is the acceleration due to the unevenness of the road by subtracting the acceleration / deceleration vertical acceleration and the vehicle characteristic parameter which is the characteristic of the vehicle from the traveling vertical acceleration. IRI can be estimated.

  The pavement information visualization means for displaying the IRI and the crack so that they can be referred to on the map is to mark the point where the crack has been confirmed according to the map displayed on the monitor of the terminal, or according to the IRI. To change the hue display. In addition to displaying directly on the map, the display that can be referred to is not limited to displaying the IRI or the presence or absence of cracks at that point indicated on the map by designating the map with a pointing device. Good. The road surface image may be captured at a specified point on the map and displayed by calling a still image or a moving image on the screen.

  According to the present invention, it is possible to carry out support for extracting attention points on all roads including residential roads and determining whether the repair work is necessary or not at a low cost. If it is possible to detect cracks on the surface layer early and repair it by repairing only the surface layer before damage progresses to the roadbed, the repair cost can be reduced to one-third or less. A system for preventive maintenance based on inspection can be prepared, and the entire life cycle cost can be reduced.

1 is a schematic diagram of a configuration as an embodiment of a system according to the present invention. Functional block diagram of an embodiment of the system according to the present invention The figure which shows the example of the image which the image analysis device analyzes The figure which shows the example of the screen visualized by the web server Flow diagram of pavement information collection and inspection method according to this invention

  Hereinafter, the present invention will be described in detail together with specific embodiments. The present invention relates to a pavement information recording apparatus 10, a pavement analysis apparatus 31, an image analysis apparatus 32, and a pavement information collection / inspection service system 30 including a web server 41, a pavement information inspection system 1 including these, and execution thereof. A method, a program for causing execution.

  The structural example of embodiment of the pavement information inspection system 1 is shown in FIG. The pavement information recording device 10 includes one or a plurality of devices, and executes means to be described later in a traveling environment mounted on the vehicle 2. The vehicle 2 does not need to be a special vehicle, and is not particularly limited as long as the vehicle 2 can be installed on a public pavement information recording apparatus 10 and can run on a public road. Here, as an apparatus constituting the pavement information recording apparatus 10, a smartphone 21 and a video camera 22 will be described as examples. It should be noted that if the smartphone 21 and the video camera 22 are mounted on separate vehicles 2, the work efficiency is low, and it takes too much time to cover even the fine life roads. It is desirable to run 2 and perform the measurement and photographing described later. However, the pavement information recording apparatus 10 does not need to be separated in this way, and may have the following configurations of both the smartphone 21 and the video camera 22 as an integrated apparatus.

  A smartphone 21 constituting the pavement information recording device 10 includes an acceleration sensor 11, an angular velocity sensor 12, a position information positioning device 14, and a recording device 15 (15a). The acceleration sensor 11 is not particularly limited as long as it can detect accelerations in the three-axis directions, and has a function more than that of a general smartphone. The angular velocity sensor 12 is a so-called gyro sensor that can detect movement in the rotational direction. The angular velocity sensor 12 is not particularly limited as long as it has more functions than those mounted on a general smartphone. The pavement information recording apparatus 10 used in the present invention preferably includes at least an acceleration sensor 11, and more preferably includes an angular velocity sensor 12.

  The position information positioning device 14 is a satellite positioning system called a so-called GPS (Global Positioning System) or a device that can acquire latitude and longitude information of the same type. The pavement information recording device 10 (smart phone 21) uses the position information positioning device 14 to execute position information acquisition means 26 that continues to acquire latitude and longitude information during traveling. In view of the necessity for analysis by the flatness analyzer 31, it is preferable that the discriminability is 10 m or less. Further, it is preferable that there is a correction capability for an error caused by reflection of radio waves from the satellite. Data that can be acquired in cooperation with the GPS function mounted on the vehicle may be used, or that that is capable of correcting misalignment.

  The recording device 15 included in the smartphone 21 constituting the pavement information recording device 10 can use a general nonvolatile memory. It may be an SD card, a compact flash or other external media 15a, or a connected magnetic disk.

  The pavement information recording device 10 (smart phone 21) uses the acceleration sensor 11 and the angular velocity sensor 12 to obtain each acceleration acquisition unit that acquires the flatness data measured during the travel as the vehicle 2 on which the pavement information recording device 10 is mounted. 25 is executed. The flatness data is data for calculating IRI that is influenced by road surface unevenness. Since the pavement information recording apparatus 10 naturally moves up and down due to the unevenness of the road surface when the vehicle 2 is traveling, it is possible to detect a damaged road surface by analyzing the vertical movement. However, since the acceleration and the angular velocity are also affected by factors other than the road surface during traveling, accuracy is insufficient when the vertical movement is determined as the road surface is damaged as it is. For this reason, it is desirable to acquire flatness data in a complex manner and correct it according to the situation. As such flatness data, for example, the vertical acceleration during traveling, which is the acceleration in the vertical direction directly measured during traveling, the angular velocity during acceleration / deceleration, which is the angular velocity due to acceleration / deceleration of the vehicle, and the acceleration / deceleration, which is the acceleration due to acceleration / deceleration. And vertical acceleration. The IRI estimation means 35 of the flatness analysis device 31 described later subtracts the acceleration acceleration / deceleration vertical acceleration and the vehicle characteristic parameter, which is a characteristic of the vehicle, from the vertical acceleration during traveling to thereby calculate the acceleration due to road unevenness. Can be extracted to estimate the IRI. In addition to estimating the IRI by measuring the acceleration and the angular velocity, it is possible to implement a method that can acquire similar parameters compatible with the IRI by measuring other elements. However, the measurement is easy and will be described later. From the viewpoint of using the analysis result, it is preferable to calculate IRI using acceleration and angular velocity.

  The pavement information recording device 10 (smart phone 21) records the flatness data measured by each acceleration acquisition unit 25 so as to be associated with the latitude / longitude information measured by the position information acquisition unit 26. Execute. The recording destination is the recording device 15. For example, the recordable data may be recorded as a table in which the flatness data and the latitude / longitude information are associated with each other, or the recording date / time of the latitude / longitude information is associated with the recording date / time of the flatness data. The formats may be recorded so that they can be referred to each other later, and the format is not particularly limited as long as they can be linked.

  The video camera 22 constituting the pavement information recording apparatus 10 is an apparatus capable of continuously capturing a moving image of the front or rear while the vehicle 2 is traveling. It is not always necessary to support moving images, and it is possible to support continuous still image shooting. However, in terms of the amount of information to be analyzed later by the image analysis device 32, moving images are desirable. The pavement information recording apparatus 10 (video camera 22) executes a road surface image acquisition unit 28 that captures a road surface image that is a moving image including a road surface or a still image as the vehicle 2 travels. The road surface image needs to reflect the road surface for analysis described later. In addition, it is desirable that other road-related objects, scenes, and the like are included as information that assists judgment when referring to map information thereafter. For example, road surface information indicating pedestrian crossings, speed limits, etc., signs, signals, guardrails, manholes, gutters, and other information attached to roads. In addition, it is more desirable to include other objects that may require maintenance in the surroundings, such as surrounding planting, tall trees, utility poles, electric wires, street lights, and the like.

  The video camera 22 constituting the pavement information recording device 10 has the same position information positioning device 14 as that of the smartphone 21 described above, or in cooperation with the position information positioning device 14 of the smartphone 21 or the vehicle 2, The position information acquisition unit 26 that continuously acquires the latitude and longitude information is executed. When the video camera 22 itself has the position information positioning device 14, latitude and longitude information may be embedded as it is in a still image or moving image to be recorded. When cooperating with the position information positioning device 14 that the smartphone 21 or the vehicle 2 has, the information may be read at any time, the recording date and time of latitude and longitude information recorded after shooting, and the recording of the road surface image that is a still image or a moving image It is advisable to make the date and time correspond. The method is not particularly limited, but the position correspondence recording unit 27 that records the latitude and longitude information of the point where the road surface image is acquired so as to be associated is executed.

  The recording device 15 included in the video camera 22 constituting the pavement information recording device 10 can use a general nonvolatile memory. It may be an SD card, a compact flash or other external media 15a, or a connected magnetic disk.

  The flatness data, the road surface image, and the latitude / longitude information associated with the flatness data recorded in the recording device 15 are transmitted via the external medium 15a which is the recording device 15, or via a cable or a network to which a device is connected. The pavement information collection / inspection service system 30 is read.

  Note that the embodiment of the pavement information recording apparatus 10 is not limited to the above configuration, and a smartphone or a tablet terminal including a high-resolution lens may also serve as the function of the video camera 22. In this case, the pavement information recording apparatus 10 is composed of one piece of hardware.

  The pavement information collection / inspection service system 30 includes a flatness analysis device 31, an image analysis device 32, and a web server 41. These devices may be independent servers or groups of servers, or may be a single server having all these functions. In any form, the server includes a recording unit and a calculation unit having sufficient calculation capability. The flatness data and the associated latitude / longitude information are recorded in the recording unit of the flatness analysis apparatus 31, and the road surface image and the associated latitude / longitude information are recorded in the image analysis apparatus 32. Each is analyzed, the result is uploaded to the web server 41, and a service for browsing the analysis result to the terminal 51 is provided.

  In addition, it is desirable to read the vehicle characteristic parameters of the vehicle 2 used for measurement together with the flatness data as information to be read by the flatness analysis device 31 because the IRI estimation accuracy is improved. The vehicle characteristic parameter may be measured and registered as an environment of the pavement information recording device 10 (smart phone 21) in the vehicle 2 before the vehicle 2 is run and each acceleration acquisition unit 25 is executed.

  As an example of acquiring the vehicle characteristic parameter, it is preferable to perform hump traveling (for example, about 10 km / h, about 100 m / h) and measure the acceleration and angular velocity. The vehicle characteristic parameter varies depending on the vehicle 2 and also varies depending on the installation status of the pavement information recording apparatus 10 (smart phone 21) installed in the vehicle 2.

  The flatness analysis device 31 executes IRI estimation means 35 that estimates IRI at each point from the flatness data. Specifically, in the flatness data, unevenness that is acceleration due to road unevenness by subtracting the acceleration / deceleration vertical acceleration, the acceleration / deceleration angular velocity, and the vehicle characteristic parameter from the traveling vertical acceleration. The acceleration is extracted and the IRI is estimated. This is because even when there is no unevenness or step on the road surface, an angular velocity in the vertical direction occurs during acceleration and deceleration, so that only the acceleration derived from the unevenness or step difference on the road surface can be extracted as much as possible. This is because it is desirable.

  On the other hand, the image analysis device 32 executes a crack detection means 37 for detecting a crack on the road surface at each point by analyzing the road surface image. As a specific configuration of the crack detection means 37, first, it is possible to detect the presence or absence of a crack by reading a large number of image data of a road surface with a crack and a road surface with no crack with a prepared neural network together with determination information. The trained image determination learning means 36 is executed to generate a learned model. As a judgment by artificial intelligence using this learned model, it is good to perform crack detection. However, although it depends on the shooting angle, the road surface on which to determine whether or not there is a crack is about the lower half of the still image or moving image, and it is recognized as a high-resolution and focused image especially in the vicinity. Part. For this reason, it is preferable to train the road surface in the vicinity of the front in the road image that is the still image or the moving image, and load the individual cells into a neural network for training.

  The detection and determination of this crack will be described with the conceptual diagram shown in FIG. First, as procedure 1, the road surface near the front in the image is squared in the same manner as the training, and each square is read by artificial intelligence using a trained neural network to determine whether or not there is a crack. . Next, as procedure 2, a “cracking rate”, which is a ratio of “cracking mass” to “total number of counts”, is calculated and classified as a damage level. For example, if the crack rate is 0% or more and less than 20%, the damage level is 1, if it is 20% or more and less than 40%, the damage level is 2, and if it is 40% or more, the damage level is 3. In the example of FIG. 3, since there are two cracked masses and the total number of masses is 15, the cracking rate is 13% and the damage level is 1.

  Further, not only the determination of cracks, but also error information on other road surfaces may be similarly determined by reading and training images corresponding to the neural network and images not so.

  Further, the flatness analysis apparatus 31 uploads the IRI of each point estimated by the IRI estimation unit 35 to the web server 41 together with the latitude / longitude information. Further, the image analysis device 32 uploads the crack rate at each point obtained by the crack detection means 37 to the web server 41 together with the latitude / longitude information. Alternatively, instead of the latitude / longitude information itself, the information may be uploaded with information that can identify the position in the format corresponding to the road information in the map information used or linked in the web server 41 in the same manner as the latitude / longitude information. In addition, the image analysis device 32 uploads the road surface image to the web server 41 together with latitude / longitude information or similar information.

  Furthermore, it is preferable that the web server 41 has map information including road information in a range to be determined by traveling. If the map information is not provided, a callable web page may be issued in cooperation with an external server map information service. Furthermore, the web server 41 displays the IRI, the crack rate, and the road surface image to the terminal 51 that has accessed via the network 42 so that the information can be referred to along the road information included in the map information. Visualization means 38 can be implemented. Displaying in a referenceable manner may be a single layer of image data in which the IRI or crack rate is entered as a color or icon on the map, or as an IRI layer or crack rate layer displayed overlapping the map layer. A format that can be arbitrarily switched between display and non-display may be used. Further, by selecting a predetermined road point on the map, the IRI, the crack rate, other information, and the road surface image 61 may be temporarily displayed as another window or another layer. In particular, it is desirable that the road surface image 61 is always developed on the map from the viewpoint of viewability, and it is desirable that the road surface image 61 corresponding to the selected point can be called.

  As a format for displaying the IRI on the map, for example, the road 60 itself can be displayed with a hue or saturation corresponding to the value of the IRI. For example, when the IRI value is good, it is blue, and when the IRI value is bad, it is displayed in a color close to red, so that it is possible to determine at a glance which part of the road causes the IRI problem.

  As the format for displaying the crack rate on the map, it may be displayed so that the color and saturation are different as in the case of IRI, or a point where a clear crack or other defect has occurred is indicated by a circle or x. A format indicated by an indicator such as a mark may be used. Note that the type and color of the indicator may be changed depending on the type of defect. Such an example is shown in FIG. In FIG. 4, the road 60 is indicated by a broken line and a solid line corresponding to the value of IRI, and cracks and other error detection points are indicated by circles 62. Further, a road surface image 61 of the point selected as a layer overlapping the window is displayed. That is, by selecting a region where it is determined that a defect or a defect such as a crack is detected in the IRI value due to color, hue, or the like, and calling the road surface image 61 of the selected point, the actual point You can check the situation. Even if there is unevenness, if it is confirmed that it is due to road surface display or manhole, it can be judged that there is no need for repair, and conversely, there is a case where it can be judged that there is a need for rush repair from designation by guardrail or sign Conceivable. In this way, it is possible to list repair priority and urgent locations and assist in making specific judgments.

  The terminal 51 using the pavement information collection / inspection system 1 (pavement information collection / inspection service system 30) according to the present invention is not particularly limited to a smartphone, a tablet, a personal computer, or the like having a network function. A dedicated application corresponding to the pavement information visualizing means 38 may be installed, or it may be browsed by a web browser so that layers can be switched and displayed.

  A series of execution procedures as an embodiment of the pavement information collection and inspection method according to the present invention is shown in the flow of FIG. First (S101), the hump running is performed on the vehicle 2 used for measurement (S102), and the vehicle characteristic parameters are calculated (S103). However, S103 may be calculated after S104 and S105. At this time, you may use the smart phone 21 used as the pavement information recording device 10. FIG.

  Next, while running on the road to be measured by the vehicle 2, recording is performed while measuring with the smartphone 21 and the video camera 22 mounted (S104). Specifically, each acceleration acquisition unit 25 that acquires the flatness data and the position information acquisition unit 26 that acquires latitude and longitude information are executed by the smartphone 21. Further, the video camera 22 executes a road surface image acquisition unit 28 for acquiring the road surface image and a position information acquisition unit 26 for acquiring latitude / longitude information. When the measurement is finished, the acquired flatness data and the road surface image are sent to the flatness analysis device 31 and the image analysis device 32 together with the latitude and longitude information (S105). In addition, the vehicle characteristic parameters are also sent to the flatness analyzer 31.

  In the analysis stage, the following steps S111 to S112 and S113 are performed in parallel. In the image analysis device 32, the data for teachers with the determination of the presence or absence of cracks is input to the road surface image, and the image determination learning means 36 for training the neural network is executed (S111). After that, the crack detection means 37 is executed using the trained learned model (S112). On the other hand, the flatness analyzer 31 executes IRI estimation means 35 for estimating IRI from the flatness data (S113).

  The flatness analysis device 31 and the image analysis device 32 that have performed the analysis upload the respective results to the web server 41 (S114). The web server 41 executes the pavement information visualization means 38 for access from the terminal 51 (S115).

DESCRIPTION OF SYMBOLS 1 Pavement information collection inspection system 2 Vehicle 10 Pavement information recording device 11 Acceleration sensor 12 Angular velocity sensor 14 Position information positioning device 15 Recording device 15a External media 21 Smartphone 22 Video camera 25 Each acceleration acquisition means 26 Position information acquisition means 27 Position corresponding recording means 28 Road surface image acquisition means 30 Pavement information collection inspection service system 31 Flatness analysis device 32 Image analysis device 35 IRI estimation means 36 Image determination learning means 37 Crack detection means 38 Pavement information visualization means 41 Web server 42 Network 51 Terminal 60 Road 61 Road surface Image 62 Circle

Claims (5)

In the driving environment mounted on the vehicle,
Each acceleration acquisition means for acquiring flatness data for calculating IRI, which is measured during traveling by an acceleration sensor, an angular velocity sensor, or both;
Road surface image acquisition means for capturing a road surface image that is a still image or a moving image including a road surface on the front or rear side while traveling by a camera;
Position information acquisition means for continuously acquiring latitude and longitude information during traveling by the position information positioning device;
Position correspondence recording means for recording the flatness data and the road surface image so as to be associated with latitude and longitude information of the acquired point;
A pavement information recording device composed of one or a plurality of devices,
A flatness analyzer for executing IRI estimation means for estimating IRI at each point corresponding to the latitude and longitude information from the flatness data;
An image analyzer for executing crack detection means for detecting cracks on the road surface at each point corresponding to the latitude and longitude information by analyzing the road surface image;
A web that can execute pavement information visualization means that receives the IRI, the crack, and the road surface image from the flatness analysis device and the image analysis device and displays them in a referable manner from a point on the map in response to a request from the terminal. Server,
Pavement information collection and inspection system. While driving the vehicle and measuring the latitude and longitude information,
Each acceleration acquisition means for acquiring flatness data for calculating IRI, which is measured during traveling by an acceleration sensor, an angular velocity sensor, or both;
Road surface image acquisition means for capturing a road surface image that is a still image or a moving image including a road surface on the front or rear side while traveling by a camera;
Performing the steps in parallel,
IRI estimation means for estimating IRI at each point corresponding to the latitude / longitude information from the flatness data;
Crack detection means for detecting cracks on the road surface at each point corresponding to the latitude and longitude information by analyzing the road surface image,
Steps to perform both
A pavement information collection and inspection method for executing the pavement information visualization means for displaying the IRI, the crack, and the road surface image so that they can be referred to from a point on the map in response to a request from the terminal. The IRI at each point corresponding to the latitude / longitude information is estimated using flatness data measured at the time of traveling by an acceleration sensor, an angular velocity sensor, or both mounted on a vehicle that continuously measures latitude / longitude information while traveling. A flatness analyzer for executing IRI estimation means;
Using a road image that is a still image or a moving image including a road surface in front or behind the vehicle that is running by a camera mounted on the vehicle, the road surface cracks at each point corresponding to the latitude and longitude information are analyzed by the road image. An image analysis device for executing crack detection means for detecting;
A web server that executes the pavement information visualization means that receives the information of the IRI, the crack, and the road surface image at each point and displays the information on the map so that the terminal can be referred to;
Pavement information collection and inspection service system. IRI at each point corresponding to the latitude / longitude information estimated using flatness data measured during travel by an acceleration sensor, an angular velocity sensor, or both mounted on a vehicle that continues to measure latitude / longitude information during travel When,
The road surface cracks at each point corresponding to the latitude and longitude information, analyzed using a road surface image that is a still image or a moving image of the front or rear road surface running by the camera mounted on the vehicle,
The road surface image;
A web server that executes a pavement information visualization unit that receives the information and displays the information on the map so that the terminal can be referred to.   A program for causing a computer to execute as the web server according to claim 4.

Images