Deterioration evaluation system, deterioration evaluation method, and recording medium

Abstract

A deterioration evaluation system according to the present disclosure comprises: an acquisition means that acquires a road image captured by a camera, said camera being mounted to a mobile body; a recognition means that recognizes an evaluation object from the road image; a region distinguishing means that distinguishes a plurality of regions having different original colors, within a region of the evaluation object in the road image; an evaluation means that uses the respective colors, in the road image, of the plurality of distinguished regions, and color variation characteristics which are established for each original color, to analyze the relationships between the colors in the road image and the original colors, and evaluates the level of deterioration of the evaluation object on the basis of the analysis results; and an output means that outputs the evaluated level of deterioration.

Description

Deterioration evaluation system, deterioration evaluation method, and recording medium

[0001] The present disclosure relates to a deterioration evaluation system and the like.

[0002] The administrator of road signs installs and inspects road signs. Since road signs become difficult to visually recognize due to aging deterioration, dirt, and being covered by trees, the administrator performs work to improve the visibility of road signs based on the inspection results. Here, it has been considered to mount a camera on a vehicle and collect images of road signs taken. By introducing a system that performs image recognition on the taken images to grasp the installation location of road signs or detect the covering of road signs by trees, the administrator can improve work efficiency.

[0003] Patent Document 1 discloses an image processing device that correctly recognizes an object such as a sign from an image taken by a camera. The image processing device of Patent Document 1 detects a sign based on a color-corrected image obtained by correcting the brightness and darkness of an image taken by a camera.

[0004] Japanese Patent Application Laid-Open No. 2018-072893

[0005] When attempting to evaluate the degree of deterioration of an object that fades due to aging deterioration, the color of the object shown in the image varies depending on the shooting conditions. The shooting conditions refer to the environment and settings when taking an image with a camera. Therefore, it is difficult to evaluate the degree of deterioration of the object to be evaluated from the image.

[0006] One of the objects of the present disclosure is to provide a deterioration evaluation system and the like that can appropriately evaluate the degree of deterioration of a fading evaluation object from an image.

[0007] A deterioration evaluation system according to one aspect of the present disclosure includes an acquisition unit that acquires a road image taken by a camera mounted on a moving body, a recognition unit that recognizes an evaluation object from the road image, a region discrimination unit that discriminates a plurality of regions in the region of the evaluation object in the road image whose original colors are different from each other, and using the color of each of the discriminated plurality of regions in the road image and the color change characteristics defined for each original color, analyzes the relationship between the color in the road image and the original color, and an evaluation unit that evaluates the degree of deterioration of the evaluation object based on the analysis result, and an output unit that outputs the evaluated degree of deterioration.

[0008] A deterioration evaluation method in one aspect of the present disclosure acquires a road image captured by a camera mounted on a mobile body, recognizes an object to be evaluated from the road image, identifies multiple regions in the road image within the region of the object to be evaluated that have different original colors, analyzes the relationship between the color in the road image and the original color using the color in the road image of each of the identified multiple regions and the color change characteristics defined for each original color, evaluates the degree of deterioration of the object to be evaluated based on the analysis results, and outputs the evaluated degree of deterioration.

[0009] A program in one aspect of this disclosure acquires a road image captured by a camera mounted on a mobile vehicle, recognizes an object to be evaluated from the road image, identifies multiple regions in the road image within the area of ​​the object to be evaluated that have different original colors, analyzes the relationship between the color in the road image and the original color using the color in the road image of each of the identified regions and the color change characteristics defined for each original color, evaluates the degree of deterioration of the object to be evaluated based on the analysis results, and causes a computer to execute a process to output the evaluated degree of deterioration. The program may be stored on a non-temporary recording medium that is readable by the computer.

[0010] One example of the effects of this disclosure is that it allows for the appropriate evaluation of the degree of deterioration of the object being evaluated, such as fading, from the image.

[0011] This is an explanatory diagram showing an example of connecting the degradation evaluation system to other devices. This is a block diagram showing an example of the configuration of the degradation evaluation system. This is a diagram showing an example of a road image. This is a graph showing an example of changes for each color according to the degree of degradation. This is a table showing an example of the degradation evaluation results. This is a diagram showing an example of a screen displayed on a user terminal. This is a flowchart showing an example of the operation of the degradation evaluation system. This is a block diagram showing an example of the configuration of the degradation evaluation system. This is a flowchart showing an example of the operation of the degradation evaluation system. This is a block diagram showing an example of the hardware configuration of a computer.

[0012] [Embodiment 1] An example of connecting the degradation evaluation system 100 to other devices in this disclosure will be explained with reference to Figure 1. The degradation evaluation system 100 is connected to the camera 10, user terminal 20, storage 40, and database 50 via a communication network 30 so as to be able to communicate. However, the degradation evaluation system 100 does not need to communicate with the camera 10 and user terminal 20. Therefore, the degradation evaluation system 100 only needs to be connected to the camera 10 and user terminal 20 as needed.

[0013] Camera 10 is mounted on, for example, a mobile device 11. Camera 10 captures images of the road and the surrounding environment. Camera 10 can be implemented, for example, by a dashcam mounted on a car. The dashcam continuously records while the car is driving on the road. However, the type of camera 10 is not limited to this. A smartphone may also be used as camera 10. Camera 10 can be mounted on various types of mobile devices 11. For example, camera 10 may be mounted on other mobile devices such as bicycles or drones.

[0014] Camera 10 generates driving data that includes captured images. The driving data includes information such as the date and time of capture and location information, in addition to the captured image data. Camera 10 transmits the driving data including images to, for example, storage 40 or degradation evaluation system 100. Location information is obtained using, for example, GNSS (Global Navigation Satellite System) or GPS (Global Positioning System). Location information is represented, for example, by latitude and longitude or a point on a map.

[0015] The user terminal 20 displays the evaluation results of the object being evaluated by the deterioration evaluation system 100. In the following description, the object being evaluated is mainly assumed to be an installation along a road (particularly a road sign). The user is assumed to be a road manager or a road sign manager. For example, a road sign manager uses the deterioration evaluation system 100 to create a repair plan for road signs. The type of user terminal 20 is not particularly limited and can be a smartphone, tablet, PC (Personal Computer), etc. For example, the user terminal 20 accesses the database 50 and displays the information stored in the database 50.

[0016] Storage 40 and database 50 are provided as needed. Storage 40 stores driving data, including images captured by camera 10. The driving data recorded in storage 40 may also include information about the route traveled by the mobile body 11 at the time the image was taken. The route traveled is identified by tracking the location information of the mobile body 11. The route traveled by the mobile body 11 is represented, for example, by the route name and whether it is traveling on the up or down line of that route. Database 50 records the processing results of the degradation evaluation system 100. These data storage mechanisms enable not only real-time processing but also post-processing using past data. Examples of database 50 formats include relational databases (RDB), NoSQL, and spreadsheet files. However, the format of database 50 is not limited to these, and any format can be used.

[0017] An example of the configuration of the degradation evaluation system 100 in this disclosure will be explained using Figure 2. The degradation evaluation system 100 comprises an acquisition unit 101, a recognition unit 102, a region discrimination unit 103, an evaluation unit 104, and an output unit 105.

[0018] The acquisition unit 101 acquires road images captured by the camera 10 mounted on the mobile body 11. Road images refer to images of the road and its surrounding environment, captured by the camera 10 mounted on the mobile body 11. Road images include evaluation targets such as road signs. Road signs are signs installed in accordance with the Road Traffic Act. Road signs come in various types, such as regulatory signs, directional signs, warning signs, and guide signs, and usually consist of a plate-shaped sign attached to a metal post. Information such as traffic regulations, direction indications, and danger warnings is displayed on the sign using colors and graphics. For example, the acquisition unit 101 acquires road images from the storage 40. Figure 3 shows an example of a road image acquired by the acquisition unit 101. In the example in Figure 3, a road sign is installed on the left side of a left-hand traffic road.

[0019] The recognition unit 102 recognizes the object to be evaluated from the road image. The object to be evaluated is an object whose original color before discoloration due to deterioration is known. In this disclosure, road signs are mainly assumed as the object to be evaluated, but the disclosure is not limited to them. The position in the road image is information indicating where in the road image the object to be evaluated is located. Specifically, the recognition unit 102 recognizes where in the road image the road sign is located. The position of the object to be evaluated in the road image can be expressed, for example, by x and y coordinates with the upper left corner of the image as the origin. In particular, the recognition unit 102 recognizes the front surface of the circular, rectangular, triangular, or other type of sign that is facing the camera 10 among the road signs.

[0020] The recognition unit 102 recognizes the object to be evaluated using any image recognition method. For example, the recognition unit 102 recognizes the object to be evaluated using a trained model that has been machine-learned to recognize the object to be evaluated. The model is trained, for example, to take an image of the object to be evaluated as input and output the correct label of the object to be evaluated attached to the input image. Input images that have been processed to change the hue and brightness of the captured image are used for training so that even degraded objects to be evaluated can be recognized. When an image is input, the model outputs the result of recognizing the region of the object to be evaluated that is shown in the image. The recognition unit 102 may also use a model that has been trained to recognize various types of objects. The recognition unit 102 may determine whether or not each pixel represents an object to be evaluated. The recognition unit 102 may detect objects in the image using semantic segmentation, classify their types, and extract their contours.

[0021] The region discrimination unit 103 identifies multiple regions in the road image that are to be evaluated and whose original colors are different from each other. Chromatic colors are colors with hue, excluding achromatic colors such as white and black. A region refers to the area in the road image that is to be evaluated. For example, the region discrimination unit 103 divides regions of different colors within a road sign based on edge detection or the magnitude of the difference in RGB (Red Green Blue) values ​​between adjacent pixels. The region discrimination unit 103 then identifies the original color of the divided region. Road signs use colors such as red, blue, white, black, yellow, green, and purple. For example, the region discrimination unit 103 uses thresholds set for RGB values ​​and hue to determine which of the known colors the original color of the region is. In the processing described later, the saturation of the evaluation target in the road image is used for evaluation, so the region discrimination unit 103 identifies regions of at least two chromatic colors. In one specific example, the area discrimination unit 103 distinguishes between areas of the road sign recognized by the recognition unit 102 that were originally red and areas that were originally blue.

[0022] A single road sign may use multiple chromatic colors. In this case, the region discrimination unit 103 identifies regions of different colors from the region of a single road sign in a single road image. The recognition unit 102 may recognize multiple road signs from a single road image. For example, road signs mounted on the same pole may be arranged horizontally or vertically and recognized from a single road image. It can be assumed that multiple road signs appearing in the same image were photographed under the same shooting conditions and are degraded to a similar degree. The region discrimination unit 103 identifies regions of different chromatic colors used in each road sign.

[0023] The evaluation unit 104 analyzes the relationship between the color in the road image and the original color using the color in each of the multiple identified areas of the road image, and the color change characteristics defined for each original color, and evaluates the degree of deterioration of the object to be evaluated based on the analysis results. The degree of deterioration is a numerical representation of the degree of deterioration of the object to be evaluated. The degree of deterioration is expressed as a value in the range of 0 to 1, for example, where 0 represents the initial state with no deterioration, and 1 represents a state of complete deterioration. The value increases as the deterioration progresses. The degree of deterioration may also be expressed by the estimated number of years since installation, if necessary. For example, a degree of deterioration of "10 years" indicates the deterioration state that can be imagined to occur after 10 years since installation. In one example, a state with an estimated age of 30 years or more may be defined as a degree of deterioration of "1". The degree of deterioration may also be expressed in multiple stages such as "large", "medium", and "small".

[0024] First, let's explain the colors in the road image that the evaluation unit 104 uses for analysis. The evaluation unit 104 uses color values, which are numerical representations of the colors in the image, for evaluation. In one example, the evaluation unit 104 uses the saturation value in HSV (Hue Saturation Value) space to analyze the relationship between the colors in the road image and the original colors. The saturation value S is calculated from the following formula, where MAX is the maximum value of the RGB values ​​and MIN is the minimum value, according to the definition.

[0025] Next, we will explain the color change characteristics determined for each original color, which the evaluation unit 104 uses for analysis. Depending on the object being evaluated, at a certain degree of deterioration after a predetermined number of years, the degree to which the saturation has decreased from the initial saturation differs from region to region depending on the original color. Applying this to a specific example, in a road sign whose degree of deterioration is about 15 years since installation, the red region may have a greater decrease in saturation than the blue region. The inventors assumed that the decrease in saturation of the paint used on the road sign's display board is expressed by an exponential function. The basis for this is thought to be that the paint decomposes due to ultraviolet light, etc. Assuming that the change in saturation of the object being evaluated as deterioration progresses is expressed by an exponential function, the saturation S of each color in the road image can be expressed by, for example, the following formula.

[0026] Here, S ０ 'x' indicates the initial saturation. D indicates the degree of deterioration of the object being evaluated. T is a constant representing the change characteristic. The change characteristic is an index that represents the degree of change in the color of the object being evaluated as deterioration progresses. The larger the value of the change characteristic T, the faster the deterioration. The change characteristic T of each color can be determined by plotting the saturation of each color for each number of years and finding an approximation curve. A time constant representing the time it takes for the saturation to reach 1 / e (approximately 37%) may also be used for the change characteristic T.

[0027] Figure 4 is a graph showing examples of color change characteristics. In Figure 4, the vertical axis represents the saturation retention rate for the theoretical saturation value unaffected by shooting conditions. The saturation retention rate is calculated by dividing the degraded theoretical saturation value by the initial theoretical saturation value. The initial saturation retention rate for each color is 100%. The horizontal axis represents the degree of degradation of the evaluated object, with the further to the right the degree of degradation, the greater the degradation and the more advanced the degradation. As can be seen from the graph, the saturation decreases as degradation progresses. Also, the degree of saturation decrease differs depending on the color. In the example in Figure 4, red tends to fade faster than blue. In the example in Figure 4, the rate of saturation decrease for yellow is intermediate between that of red and blue.

[0028] Note that the color change characteristics may vary depending on the type of paint. Figure 4 shows an example where the color change characteristics differ depending on the color type, but this is not an exhaustive example. The color change characteristics defined for each original color may also be common across different colors.

[0029] Next, the evaluation unit 104 will explain its method for analyzing the relationship between the colors in the road image and the original colors. To analyze the relationship between the colors in the road image and the original colors, the following factors are considered: color changes due to degradation, the degradation rate of each color, and color changes due to shooting conditions. The saturation of the colors in the image varies depending on the shooting conditions. Shooting conditions refer to the environment and settings when the camera 10 takes an image. Specifically, these include weather, sunlight intensity, shooting time, and camera exposure settings. These conditions affect the color and brightness of the captured image.

[0030] In one example, the evaluation unit 104 sets a mathematical formula for each of the multiple identified regions that represents the relationship between the color value (e.g., saturation S) in the road image and the theoretical color value corresponding to the degree of deterioration. The theoretical color value corresponding to the degree of deterioration is represented by the change characteristic T for each color and the degree of deterioration D.

[0031] Saturation S of the red area in the road image ｒ , and the saturation S of the blue area in the road image ｂ The following formula can be set for this. The change characteristic of the red is T ｒ , the blue color change characteristics T ｂ This is shown. The degree of deterioration of the subject being evaluated is indicated by a deterioration level of D.

[0032] The saturation change E is an index that represents the ratio of the actual color and the color saturation in the road image, which result from differences in shooting conditions.

[0033] Here, the evaluation unit 104 sets up a system of simultaneous equations using multiple mathematical formulas set for each region. A system of simultaneous equations refers to a set of equations used to find a solution that satisfies multiple formulas simultaneously. It is assumed that the degree of change E in saturation due to shooting conditions is constant, even for regions of different colors. The inventors assumed that the ratio of the saturation of the actual color being evaluated to the saturation of the color in the road image is constant regardless of the color. That is, they assumed that in the case of direct sunlight, all colors become equally vivid. Also, the value of the degree of deterioration D is naturally common for multiple regions of a single road sign. When the above formula is set for regions of separate road signs, it is assumed that the two road signs were installed at the same time and that the degree of deterioration D is common to both.

[0034] By setting up a system of equations including these two formulas, it is possible to determine the two unknowns: the degree of change E in saturation and the degree of degradation D due to the shooting conditions. The evaluation unit 104 calculates the saturation values ​​of the colors in each region of the road image with different original colors in order to determine the unknowns. For example, the evaluation unit 104 obtains the average of the RGB values ​​of the red region of the road sign and the average of the RGB values ​​of the blue region, and calculates the saturation. The evaluation unit 104 then enters the saturation of each color and a predetermined change characteristic T into each formula. ｒ , T ｂ By substituting the values, the degree of deterioration D, which is the solution to the system of equations, is calculated. In this way, the evaluation unit 104 can analyze the relationship between the color in the road image and the original color by solving the above system of equations and calculating the degree of change E and the degree of deterioration D. The evaluation unit 104 evaluates the degree of deterioration by obtaining the analysis results.

[0035] The evaluation area in the road image may contain areas with three or more colors. Therefore, for example, the evaluation unit 104 analyzes the area with the two colors that have the greatest difference in color change characteristics. For example, in two chromatic colors, the greater the difference in change characteristics, the greater the difference in saturation retention rate at a predetermined degree of deterioration. This makes it less likely to pick up noise due to color measurement errors, errors in area judgment, dirt on the evaluation area, etc., and allows for a more accurate determination of the degree of deterioration. When the road image contains areas with three or more chromatic colors, the evaluation unit 104 selects the area with two chromatic colors. Alternatively, the evaluation unit 104 may analyze the area with the greatest degree of change in color value in relation to the progression of deterioration of the evaluation area.

[0036] Alternatively, the evaluation unit 104 may analyze a color region specified by the user. The user specifies two colors from the original colors of the road sign in the image that are suitable for analysis. In this case, the evaluation unit 104 determines the saturation of the specified color region. The evaluation unit 104 may also analyze a region specified by the user. The user specifies a region suitable for evaluation, excluding parts that are not road signs and dirty parts.

[0037] The output unit 105 outputs the degree of deterioration evaluated by the evaluation unit 104. The output degree of deterioration is recorded in the database 50. The output format is not particularly limited and can be a table format, CSV (comma separated values) format, etc. An example of outputting the evaluated degree of deterioration in a table format is shown using Figure 5. In the example in Figure 5, the road image shooting location information (latitude and longitude), the road image, and the evaluated degree of deterioration are shown. The photographed signs are associated with the sign ID (identifier) ​​recorded in the database 50 and the location information based on the location information of the road image shooting location. This updates the degree of deterioration information in the database 50. By combining digital automatic detection of road signs with GPS location information, more accurate and efficient centralized management is achieved compared to manual input by visual inspection.

[0038] The output unit 105 may output the degree of deterioration to the user terminal 20. At this time, a part of the function of the output unit 105 may be realized by the user terminal 20. The information displayed becomes useful reference information when the administrator creates a repair plan. The output unit 105 may cause the user terminal 20 to display the screen of FIG. 6 including the information on the degree of deterioration. The screen of FIG. 6 includes the captured road image, an enlarged view of the road sign recognized from the road image, and the evaluated degree of deterioration. Further, the screen of FIG. 6 includes the latitude and longitude information of the road sign and a map indicating the geographical location where the road sign is installed. The output unit 105 may plot the geographical location of the evaluation target on the map and display it with color-coding according to the degree of deterioration. By the user selecting a point on the map, detailed information on the road sign at that point, such as the screen of FIG. 6, is displayed.

[0039] In one example, the output unit 105 may have a filtering function of displaying only evaluation targets whose degree of deterioration exceeds a threshold value. The threshold value may be set by the user. The output unit 105 may display a predetermined number of road signs in descending order of priority determined by the traffic volume and the degree of deterioration. The priority is an index indicating the necessity of repairing the road sign that is the evaluation target. The traffic volume of a road refers to the number of vehicles passing through a specific road section within a certain period of time. The traffic volume is used as an index indicating the importance and congestion status of the road.

[0040] An operation example of the deterioration evaluation system 100 in the present disclosure will be described using FIG. 7. The deterioration evaluation system 100 starts the process of FIG. 7, for example, in response to the accumulation of road images in the storage 40.

[0041] In step S1, acquisition unit 101 acquires a road image captured by camera 10 mounted on mobile body 11. In step S2, recognition unit 102 recognizes an evaluation target from the road image acquired by acquisition unit 101. In step S3, region discrimination unit 103 discriminates a plurality of regions having different original colors and being chromatic colors from the regions of the evaluation target in the road image recognized by recognition unit 102. In step S4, evaluation unit 104 analyzes the relationship between the color in the road image and the original color by using the color change characteristics corresponding to the color in each of the discriminated plurality of regions and the degree of degradation determined for each original color. Then, evaluation unit 104 evaluates the degree of degradation of the evaluation target based on the analysis result. In step S5, output unit 105 outputs the degree of degradation evaluated by evaluation unit 104.

[0042] As described above, degradation evaluation system 100 ends the processing of FIG. 7.

[0043] According to Embodiment 1, the degree of degradation of the evaluation target that fades can be appropriately evaluated from an image. The reason is that evaluation unit 104 analyzes the relationship between the color in the road images of a plurality of regions with different colors and the original color by using the change characteristics determined for each original color of the evaluation target, and evaluates the degree of degradation, so that the influence of the shooting conditions can be excluded.

[0044] [Modification Example] Embodiment 1 can be modified as follows. These modification examples improve or expand specific aspects while maintaining the basic configuration and processing flow of Embodiment 1. These modification examples can be applied alone or in combination.

[0045] Recognition unit 102 may recognize the type of road sign. Region discrimination unit 103 may discriminate regions of different colors based on the recognized type of road sign, such as vehicle stop, temporary stop, and parking prohibition. By region discrimination unit 103 discriminating regions based on the type of road sign, more accurate discrimination is made possible. Also, since similar colors such as purple and red can be appropriately discriminated, evaluation unit 104 can use appropriate change characteristic values.

[0046] The recognition unit 102 recognizes the type of road sign, for example, using a trained model that has been trained to recognize the type of road sign. Since there are rules governing the order in which road signs are arranged on the same support post, the recognition unit 102 may use the order in which the road signs are arranged to identify the type. Alternatively, if the location and type of road signs are managed in a ledger, the recognition unit 102 may recognize the type of road sign by searching for the corresponding road sign based on the location where the image was taken. For example, the recognition unit 102 may refer to the ledger recorded in the database 50.

[0047] The region discrimination unit 103 selects a standard layout template from the database 50 that corresponds to the type of road sign recognized. This template contains information about the position and shape of each colored region. The region discrimination unit 103 overlays the selected template onto the image of the recognized road sign. Then, based on the aligned template, each colored region is extracted.

[0048] The evaluation unit 104 may evaluate signs of a type specified by the user. This allows for analysis focused on specific types of signs and intensive evaluation of high-priority signs.

[0049] In some cases, it is desirable to exclude certain areas of road signs from evaluation. Specifically, areas where the colored reflective sheeting attached to the sign has peeled off may be white or the underlying metal color may be visible, making evaluation based on the change characteristics representing fading due to pigment decomposition difficult. Also, rusted areas obscure the original color of the sign, making accurate color evaluation impossible. In areas that are bent, the shape of the road sign changes, making it difficult to properly distinguish the area.

[0050] To address these issues, the recognition unit 102 analyzes the shape of the road sign and detects deviations from the standard shape. The recognition unit 102 also recognizes abnormalities such as peeling and rust. Based on the information from the recognition unit 102, the area discrimination unit 103 excludes the areas where abnormalities were detected and identifies only the healthy areas. The evaluation unit 104 evaluates the degree of deterioration using the areas selected by the area discrimination unit 103. The output unit 105 may output information on the detected abnormalities in addition to the evaluation results.

[0051] The recognition unit 102 may identify the road image in which the road sign is most prominently displayed from among a series of images of the same road sign taken consecutively. The larger the road sign is displayed, the higher the resolution and the more accurate the color measurement becomes. The recognition unit 102 passes the identified road image to the region discrimination unit 103. The region discrimination unit 103 uses the received road image to distinguish between regions of different colors within the road sign. The region discrimination unit 103 may identify the two largest color regions from the distinguished regions. The region discrimination unit 103 passes the information of the two selected color regions to the evaluation unit 104. The evaluation unit 104 uses the received information of the two color regions to evaluate the degree of deterioration.

[0052] Embodiment 1 describes an example in which multiple color regions recognized from a single road image are used for evaluation. However, the results of recognizing different road signs from multiple road images may also be used. When using multiple images of multiple road signs, each containing different chromatic colors, the following points should be noted: When measuring the colors of separate road signs, the road signs must be adjacent to each other and installed at the same time.

[0053] The proximity of road signs can be determined by using location information from the image capture site or by analyzing whether consecutively captured frames were taken within a short period of time. Adjacent road signs are expected to deteriorate to a similar degree because they are in similar environments. Whether they were installed at the same time can be determined by referring to the installation dates recorded in database 50. If the installation date record cannot be referenced, signs located close together can be treated as having been installed at the same time. Signs with similar degrees of rust can also be treated as having been installed at the same time. Rust generally progresses from top to bottom. Based on this process, it may be possible to estimate the elapsed time since installation by evaluating the extent to which the signs are covered in rust.

[0054] In Embodiment 1, an example was described in which an exponential function is used as the mathematical formula representing the relationship between the degree of degradation and the change in color, but it is also possible to use other models. For example, blue degrades relatively slowly and can sometimes be approximated by a linear model. In addition, logarithmic models or nonlinear models may be used depending on how the color changes.

[0055] In Embodiment 1, an example was described in which the degree of deterioration is evaluated by solving a system of equations. The evaluation unit 104 may evaluate the degree of deterioration by other methods.

[0056] One method involves using a table that represents the relationship between the degree of degradation and the change in color. In this method, the first input is the color values ​​of the two regions of the image and the original color value, for a total of four values. Next, the evaluation unit 104 searches the table for the combination that is closest to the four values. The evaluation unit 104 outputs the degree of degradation corresponding to the matching combination.

[0057] Another method involves using a machine learning model. This method also takes four input values: the color values ​​in the two regions of the image and the original color value. The evaluation unit 104 inputs these values ​​into the trained model. The degradation level output by the model is then used as the degradation level evaluation. The machine learning model learns color change patterns, color change trends at different degradation stages, and the relationship between elapsed time and color change.

[0058] The process described above, which uses tables and machine learning models, is equivalent to a process of analyzing the relationship between the colors in road images and the original colors, using the colors in the road images and the color change characteristics defined for each original color.

[0059] Embodiment 1 describes a method for evaluating the degree of deterioration using saturation values. However, other numerical values ​​representing color, such as brightness, may be used to evaluate the degree of deterioration. Embodiment 1 also describes a method for evaluating the degree of deterioration using regions that are chromatic colors with different original colors. However, the color of a road image in a region that was originally achromatic may also be used to evaluate the degree of deterioration. For example, a region that was originally white will become dirty and change to black or brown over time. Also, a black region will change to white due to the peeling of paint or sheets. For such changes, a change characteristic representing the relationship between brightness and degree of deterioration can be determined and set in advance, and the degree of deterioration can be evaluated by inputting the colors of road images in multiple regions, including achromatic regions.

[0060] The output unit 105 may output locations where the deterioration rate of the evaluated object is faster than a predetermined standard, calculated from the evaluated degree of deterioration, the past degree of deterioration of the evaluated object, and the elapsed time. The deterioration rate refers to the rate of change over time of the degree of deterioration of the evaluated object. This makes it possible to identify road signs that are deteriorating faster than usual. By identifying locations with a high rate of deterioration, road signs at those locations can be inspected more frequently, allowing for early detection of deterioration. Furthermore, the causes of high deterioration rates at specific locations can be analyzed and used for future installation and maintenance. At locations with high deterioration rates, maintenance such as adding protective coatings can be implemented to slow down the progression of deterioration. The output unit 105 can plot the locations on a map or display them in a list format, allowing administrators to efficiently consider countermeasures. The output unit 105 may also provide a function to narrow down road signs based on the deterioration rate, allowing users to extract targets based on arbitrary criteria.

[0061] [Embodiment 2] An example of the configuration of the degradation evaluation system 200 in this disclosure will be described with reference to Figure 8. The degradation evaluation system 200 according to Embodiment 2 differs from the degradation evaluation system 100 according to Embodiment 1 in that it comprises a determination unit 106, a prediction unit 107, and a correction unit 108. Embodiments 1 and 2 can be combined as appropriate, and for example, the determination unit 106, the prediction unit 107, and the correction unit 108 can each be applied to the degradation evaluation system 100 as needed. The configuration of the degradation evaluation system 200 that is the same as that of the degradation evaluation system 100 will not be described.

[0062] The determination unit 106 determines whether the road sign to be evaluated should be repaired based on the degree of deterioration evaluated by the evaluation unit 104. Specifically, it determines that the road sign should be repaired if the degree of deterioration exceeds a preset threshold. This threshold is set appropriately according to the type of road sign, the importance of the installation location, the budget situation, etc. Repair refers to work to restore the function and performance of the road sign being evaluated. Specifically, this includes reapplying reflective sheets to deteriorated road signs, repainting, replacing parts, cleaning, or complete replacement. The repair method is appropriately selected according to factors such as the degree of deterioration and importance of the road sign being evaluated, and the budget.

[0063] The determination unit 106 may have a function to determine whether or not repairs are necessary for the items under evaluation, taking into account not only a threshold for the degree of deterioration but also multiple factors. For example, it may determine whether or not repairs are necessary for the items under evaluation based on priority determined according to the degree of deterioration and the cost of repair. Specifically, it may determine that items under evaluation that can be repaired within the budget should be repaired first. In this case, the time and cost of the repair, as well as the annual budget and available working hours, should be taken into consideration. The budget refers to, for example, the total amount of financial resources allocated to the repair of road signs. The budget is usually set annually and determined by the relevant body, such as the road administrator or local government.

[0064] In one example, the determination unit 106 determines whether the road sign to be evaluated needs repair based on the type of road sign, the volume of road traffic, or the surrounding environment, as well as the repair cost. For example, in the determination based on the type of sign, regulatory signs are given a higher priority than other types of signs. Signs installed on busy main roads or at accident-prone locations are given a higher priority. The surrounding environment refers to the conditions around the location where the road sign to be evaluated is installed. Specifically, this includes geographical characteristics such as coastal areas, mountainous areas, and urban areas, as well as the presence or absence of facilities such as schools. Signs installed in environments prone to deterioration, such as coastal areas, or in areas where accident prevention is particularly important, such as near schools, are also likely to be given priority for repair. Furthermore, if there are multiple road signs in need of repair nearby, it may be considered to repair them all together for efficient work. The determination unit 106 can also use a trained model to comprehensively analyze these various factors and make an optimal determination of whether repair is necessary. This model takes factors such as sign type, importance of installation location, degree of deterioration, traffic volume, surrounding environment, and repair costs as inputs, and outputs whether repairs are necessary and their priority.

[0065] The output unit 105 outputs the determination results from the determination unit 106. The output information includes, for example, whether or not repairs are necessary for each evaluated object, a list of locations determined to require repair, and their display on a map. It can also provide the number of evaluated objects determined to require repair, their proportion to the total, and information on the distribution of deterioration levels. The deterioration level distribution here indicates the trend of deterioration levels for all evaluated objects and is expressed in a format such as a histogram. This allows road administrators to grasp the overall deterioration situation and use it to formulate repair plans.

[0066] The output unit 105 displays the results of the deterioration evaluation system 200's determination of whether repairs are necessary, and also provides a function that allows the user to individually select whether repairs are necessary. The user can select whether repairs are necessary based on their own judgment, separate from the system's decision, and input the reason as a comment. Furthermore, a function allows users to view all locations that the system or the user has determined require repair, displaying these locations in a list format and on a map. Additional information such as the reason for repair and priority is also displayed, enabling efficient decision-making.

[0067] The output unit 105 has a function to automatically create a repair plan based on the collected data and judgment results. This automatically created repair plan includes a priority list of repair targets, recommended repair timing, estimated repair costs, and estimates of the number of workers and working hours required. The user can review the automatically created repair plan and modify it as needed. Modifiable items include whether individual evaluated targets require repair, repair priorities, adjustments to repair timing, and selection of repair methods (replacement, partial repair, cleaning, etc.). Furthermore, the output unit 105 may output a list including the types of road signs to be ordered in preparation for replacement, the required quantity of each type, and recommended delivery dates.

[0068] The prediction unit 107 predicts the future degree of deterioration of the object being evaluated. For example, the prediction unit 107 uses the evaluated degree of deterioration, the past degree of deterioration of the object being evaluated, and the elapsed time to predict the future degree of deterioration. The past degree of deterioration is a numerical representation of the degree of deterioration of the object being evaluated at a past point in time. The elapsed time refers to the period from the time when the past degree of deterioration was evaluated to the current evaluation time. It is usually expressed in units of time such as days or years. The deterioration rate is an indicator of how quickly the deterioration of the object being evaluated is progressing. Specifically, for example, it is calculated as the value obtained by dividing the difference between the past degree of deterioration and the current degree of deterioration by the elapsed time.

[0069] In one example, the past deterioration level is the deterioration level evaluated using road images taken of the same object to be evaluated in the past. The prediction unit 107 obtains the past deterioration level recorded in the database 50. In another example, the past deterioration level is the deterioration level of the object to be evaluated at the time of installation. At the time of installation, the object to be evaluated can be treated as not having deteriorated.

[0070] The determination unit 106 determines whether future repairs to the object being evaluated are necessary based on the predicted future degree of deterioration. The determination unit 106 may also determine when repairs will be necessary based on the future degree of deterioration. For example, based on the current degree of deterioration and rate of deterioration, it may determine that repairs are necessary when the estimated age reaches a degree of deterioration equivalent to 20 years, or when the degree of deterioration exceeds a specific threshold such as 0.5 or 0.8.

[0071] The output unit 105 creates and outputs a future repair plan based on the prediction of future deterioration by the prediction unit 107 and the determination of whether future repairs are necessary by the determination unit 106. This future repair plan includes, for example, the predicted timing when repairs will be needed, the repair order based on priority, the expected number of repair targets and estimated costs for each year, and a proposal for a medium- to long-term budget plan. The output unit 105 displays this information in an easy-to-understand visual format. For example, it shows the future deterioration of each evaluation target with color-coded pins on a map and displays the repair plan in a timeline format. It also uses graphs to show the progression of deterioration and the timing of repairs, allowing users to intuitively understand the future situation.

[0072] The correction unit 108 corrects the color values ​​of the area to be evaluated in the road image according to the color values ​​of the reference object captured in the image by the camera. This correction reduces the influence of lighting conditions and weather during shooting, enabling more accurate measurement of color and saturation. The evaluation unit 104 evaluates the degree of deterioration of the area to be evaluated based on the analysis results using the corrected color values.

[0073] Several methods are used for calibration to correct the image. One method involves adjusting the overall color tone of the image using a black and white color sample. Existing techniques are used to adjust the color tone from the color sample. Furthermore, assuming that the colors of road markings are relatively resistant to fading, they can also be used as a reference. Road markings refer to signs and symbols drawn on the road surface. These include white and yellow lines that separate lanes, pedestrian crossings, stop lines, and arrows. In particular, white road markings serve as a valid reference. The correction unit 108 adjusts the overall color tone of the image using the color values ​​of these reference objects. For example, it adjusts the color balance of the entire image so that the white parts of the reference objects become true white.

[0074] The recognition unit 102 recognizes reference objects using the same technology as that used to recognize the object to be evaluated. The recognition unit 102 may recognize reference objects using the same model that was trained to recognize the object to be evaluated. Alternatively, the recognition unit 102 may recognize reference objects using a different model than the one trained to recognize the object to be evaluated. The recognition unit 102 can recognize which region of the road image contains the reference object.

[0075] An example of the operation of the deterioration evaluation system 200 in this disclosure will be explained using Figure 9. The deterioration evaluation system 200 starts the processing shown in Figure 9, for example, when road images are accumulated in the storage 40.

[0076] In step S21, the acquisition unit 101 acquires a road image captured by the camera 10 mounted on the mobile body 11. In step S22, the recognition unit 102 recognizes a reference object and an object to be evaluated from the road image acquired by the acquisition unit 101. In step S23, the region discrimination unit 103 identifies multiple regions in the road image recognized by the recognition unit 102 that are chromatic colors with different original colors. In step S24, the correction unit 108 corrects the color values ​​of the regions to be evaluated based on the color of the reference object. In step S25, the evaluation unit 104 analyzes the relationship between the color in the road image and the original color using the color in the road image for each of the multiple regions identified, and the color change characteristics according to the degree of deterioration determined for each original color. Then, the evaluation unit 104 evaluates the degree of deterioration of the object to be evaluated based on the analysis results. In step S26, the determination unit 106 determines whether to repair the object to be evaluated based on the degree of deterioration evaluated by the evaluation unit 104. In step S27, the output unit 105 outputs the degree of deterioration evaluated by the evaluation unit 104. With this, the deterioration evaluation system 200 completes the process shown in Figure 9.

[0077] According to Embodiment 2, in addition to the effects of Embodiment 1, the following effects can be obtained. The determination unit 106 and output unit 105 can assist in determining whether or not repairs are necessary for the object to be evaluated. The prediction unit 107 can predict the future degree of deterioration of the object to be evaluated, enabling proactive and efficient maintenance. This reduces the need for sudden repairs and enables planned budget allocation and work execution. Furthermore, the correction unit 108 corrects the color values, making it possible to improve the evaluation accuracy of images taken under different environmental conditions.

[0078] In each of the embodiments described above, an example was given in which the present disclosure is applied to evaluating the degree of deterioration of road signs from images captured by a camera 10 mounted on a mobile body 11. A fixed camera or a camera held by the user may be used as the camera 10. Furthermore, the present disclosure is also applicable to the evaluation of other objects to be evaluated. For example, the present disclosure can be applied to the evaluation of the degree of deterioration of buildings from the colors of bridges and building exteriors painted with two or more chromatic colors with known change characteristics. It can also be applied to the weather resistance evaluation of other products and to the quality control of printed materials such as advertising signs and posters.

[0079] [Hardware Configuration] In each of the embodiments described above, each component of the degradation evaluation system 100, 200 represents a functional unit block. Some or all of the components of the degradation evaluation system 100, 200 may be implemented by any combination of computer 500 and program.

[0080] Figure 10 is a block diagram showing an example of the hardware configuration of computer 500. Referring to Figure 10, computer 500 includes, for example, a processor 501, ROM (Read Only Memory) 502, RAM (Random Access Memory) 503, a program 504, a storage device 505, a drive device 507, a communication interface 508, an input device 509, an output device 510, an input / output interface 511, and a bus 512.

[0081] The processor 501 controls the entire computer 500. The processor 501 may be, for example, a CPU (Central Processing Unit). The number of processors 501 is not particularly limited; there may be one or more processors 501.

[0082] Program 504 includes instructions for implementing each function of the degradation evaluation systems 100 and 200. Program 504 is pre-stored in ROM 502, RAM 503, and storage device 505. The processor 501 implements each function of the degradation evaluation systems 100 and 200 by executing the instructions contained in program 504. RAM 503 may also store data processed in each function of the degradation evaluation systems 100 and 200.

[0083] The drive device 507 reads and writes to the recording medium 506. The communication interface 508 provides an interface with the communication network. The input device 509 is, for example, a mouse or keyboard, and receives information input from an administrator or the like. The output device 510 is, for example, a display, and outputs (displays) information to the administrator or the like. The input / output interface 511 provides an interface with peripheral devices. The bus 512 connects each of these hardware components. The program 504 may be supplied to the processor 501 via the communication network, or it may be stored in the recording medium 506 beforehand, read by the drive device 507, and supplied to the processor 501.

[0084] Note that the hardware configuration shown in Figure 10 is an example, and other components may be added, or some components may be omitted.

[0085] There are various ways to implement the degradation evaluation systems 100 and 200. For example, the degradation evaluation systems 100 and 200 may be implemented by any combination of different computers and programs for each component. Alternatively, the multiple components of the degradation evaluation systems 100 and 200 may be implemented by any combination of a single computer and program.

[0086] Furthermore, at least a portion of the degradation evaluation systems 100 and 200 may be provided in SaaS (Software as a Service) format. That is, at least a portion of the functions for realizing the degradation evaluation systems 100 and 200 may be executed by software that runs over a network.

[0087] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the configuration and details of the present disclosure are possible, as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, the configurations in each embodiment can be combined with one another, as long as they do not depart from the scope of the present disclosure.

[0088] Some or all of the above embodiments may be described as follows, but are not limited to the following:

[0089] [Note 1] A deterioration evaluation system comprising: acquisition means for acquiring a road image captured by a camera mounted on a mobile body; recognition means for recognizing an object to be evaluated from the road image; region discrimination means for distinguishing a plurality of regions in the road image from which the original colors differ from each other among the regions of the object to be evaluated; evaluation means for analyzing the relationship between the color in the road image and the original color using the color in the road image of each of the plurality of regions that have been distinguished, and the color change characteristics determined for each original color, and evaluating the degree of deterioration of the object to be evaluated based on the analysis results; and output means for outputting the evaluated degree of deterioration.

[0090] [Note 2] The deterioration evaluation system described in Note 1, wherein the evaluation means analyzes the relationship by solving a plurality of mathematical formulas that represent the degree of decrease in saturation with respect to the deterioration level, which are set assuming that the degree of change in saturation due to shooting conditions is constant regardless of color, using the color saturation in the road image of each of the plurality of regions that have been identified, and the change characteristics that represent the degree of decrease in saturation according to the deterioration level.

[0091] [Note 3] The deterioration evaluation system described in Note 2, wherein the formula is a formula that expresses the degree of decrease in saturation relative to the degree of deterioration as an exponential function.

[0092] [Appendix 4] The deterioration evaluation system according to any one of Appendix 1 to 3, further comprising a determination means for determining whether the object to be evaluated should be repaired based on the evaluated degree of deterioration, wherein the output means outputs the determination result.

[0093] [Note 5] The deterioration evaluation system described in Note 4, wherein the determination means determines to repair the evaluation targets that can be repaired within the budget, based on the priority and repair costs determined according to the degree of deterioration.

[0094] [Note 6] The deterioration evaluation system described in Note 4 or 5, wherein the determination means determines to repair the evaluated items that can be repaired within the budget, based on the priority and repair costs determined according to the road traffic volume or surrounding environment.

[0095] [Appendix 7] The deterioration evaluation system according to any one of Appendix 4 to 6, further comprising a prediction means for predicting the future degree of deterioration based on the deterioration rate of the subject to be evaluated, calculated from the evaluated degree of deterioration and the past degree of deterioration and elapsed time of the subject to be evaluated, wherein the determination means determines whether future repairs of the subject to be evaluated are necessary based on the future degree of deterioration.

[0096] [Note 8] The deterioration evaluation system described in Note 7, wherein the determination means determines the point in time when repairs will be necessary based on the future degree of deterioration.

[0097] [Note 9] The deterioration evaluation system described in Note 7 or 8, wherein the past deterioration level is the deterioration level evaluated using road images taken of the subject to evaluation in the past.

[0098] [Note 10] The deterioration evaluation system described in any one of Notes 7 to 9, wherein the past deterioration level is the deterioration level at the time of installation of the object to be evaluated, and indicates that the object to be evaluated has not deteriorated.

[0099] [Note 11] The degradation evaluation system according to any one of Notes 1 to 10, wherein the output means outputs the geographical location of the evaluation target where the degree of degradation exceeds a threshold.

[0100] [Note 12] The degradation evaluation system according to any one of Notes 1 to 11, wherein the output means outputs points where the degradation rate of the subject to be evaluated is faster than a predetermined standard, calculated from the evaluated degradation level, the past degradation level of the subject to be evaluated, and the elapsed time.

[0101] [Note 13] A deterioration evaluation system according to any one of Notes 1 to 12, comprising a correction means for correcting the color value of the area to be evaluated in the road image according to the color value of a reference object captured in the image by the camera, wherein the evaluation means evaluates the degree of deterioration of the object to be evaluated based on the analysis results using the corrected color value.

[0102] [Note 14] The reference object is the road markings visible in the road image, as described in Note 13, for the deterioration evaluation system.

[0103] [Note 15] The deterioration evaluation system according to any one of Notes 1 to 14, wherein the evaluation means targets the region of two chromatic colors where the difference in the change characteristics of the color values ​​according to the degree of deterioration is the largest.

[0104] [Note 16] The evaluation means is a degradation evaluation system according to any one of Notes 1 to 15, wherein the evaluation means targets a color region specified by the user for analysis.

[0105] [Note 17] The evaluation means is a degradation evaluation system according to any one of Notes 1 to 16, wherein the evaluation means targets an area specified by the user for analysis.

[0106] [Note 18] The evaluation target is a road sign, and the deterioration evaluation system is as described in any one of Notes 1 to 17.

[0107] [Note 19] A deterioration evaluation method comprising: acquiring a road image captured by a camera mounted on a mobile body; recognizing an object to be evaluated from the road image; identifying multiple regions in the road image of the object to be evaluated that have different original colors from each other; analyzing the relationship between the color in the road image and the original color using the color in the road image of each of the identified multiple regions and the color change characteristics defined for each original color; evaluating the degree of deterioration of the object to be evaluated based on the analysis results; and outputting the evaluated degree of deterioration.

[0108] [Note 20] A non-temporary recording medium that records a program that causes a computer to execute a process which includes acquiring a road image taken by a camera mounted on a mobile body, recognizing an object to be evaluated from the road image, identifying multiple regions in the road image of the object to be evaluated that have different original colors from each other, analyzing the relationship between the color in the road image and the original color using the color in the road image of each of the identified multiple regions and the color change characteristics defined for each original color, evaluating the degree of deterioration of the object to be evaluated based on the analysis results, and outputting the evaluated degree of deterioration.

[0109] Some or all of the configurations described in Appendix 2-18, which are dependent on Appendix 1 above, may also be dependent on Appendix 19-20 in the same manner as in Appendix 2-18. Not limited to Appendix 1 and 19-20, some or all of the configurations described as appendices may also be dependent on various hardware, software, various recording devices or systems for recording software, without departing from the embodiments described above.

[0110] 100, 200... Degradation evaluation system, 101... Acquisition unit, 102... Recognition unit, 103... Area discrimination unit, 104... Evaluation unit, 105... Output unit, 106... Judgment unit, 107... Prediction unit, 108... Correction unit, 10... Camera, 11... Mobile device, 20... User terminal, 30... Communication network, 40... Storage, 50... Database

Claims

1. A deterioration evaluation system comprising: acquisition means for acquiring road images captured by a camera mounted on a mobile body; recognition means for recognizing an object to be evaluated from the road image; region discrimination means for distinguishing a plurality of regions in the road image from which the original colors differ from each other; evaluation means for analyzing the relationship between the color in the road image and the original color using the color in the road image of each of the plurality of regions that have been distinguished, and the color change characteristics determined for each original color, and evaluating the degree of deterioration of the object to be evaluated based on the analysis results; and output means for outputting the evaluated degree of deterioration.

2. The deterioration evaluation system according to claim 1, wherein the evaluation means analyzes the relationship by solving a plurality of mathematical formulas that represent the degree of decrease in saturation with respect to the deterioration level, which are set assuming that the degree of change in saturation due to shooting conditions is constant regardless of color, using the color saturation in the road image of each of the plurality of regions that have been identified, and the change characteristics that represent the degree of decrease in saturation according to the deterioration level.

3. The deterioration evaluation system according to claim 2, wherein the formula is a formula that expresses the degree of decrease in saturation relative to the degree of deterioration as an exponential function.

4. A deterioration evaluation system according to any one of claims 1 to 3, further comprising determination means for determining whether the object to be evaluated should be repaired based on the evaluated degree of deterioration, wherein the output means outputs the determination result.

5. The deterioration evaluation system according to claim 4, wherein the determination means determines to repair the items to be evaluated that can be repaired within the budget, based on the priority determined according to the degree of deterioration and the cost of repair.

6. The deterioration evaluation system according to claim 4 or 5, wherein the determination means determines to repair the evaluated items that can be repaired within the budget, based on the priority and repair costs determined according to the road traffic volume or surrounding environment.

7. A deterioration evaluation system according to any one of claims 4 to 6, further comprising a prediction means for predicting the future degree of deterioration based on the deterioration rate of the object to be evaluated, calculated from the evaluated degree of deterioration and the past degree of deterioration and elapsed time of the object to be evaluated, wherein the determination means determines whether future repairs of the object to be evaluated are necessary based on the future degree of deterioration.

8. The deterioration evaluation system according to claim 7, wherein the determination means determines the point in time when repair will be necessary based on the future degree of deterioration.

9. The deterioration evaluation system according to claim 7 or 8, wherein the past deterioration level is the deterioration level evaluated using road images taken of the subject to evaluation in the past.

10. The deterioration evaluation system according to any one of claims 7 to 9, wherein the past deterioration level is the deterioration level at the time of installation of the object to be evaluated, and indicates that the object to be evaluated has not deteriorated.

11. The degradation evaluation system according to any one of claims 1 to 10, wherein the output means outputs the geographical location of the evaluation target where the degree of degradation exceeds a threshold.

12. The degradation evaluation system according to any one of claims 1 to 11, wherein the output means outputs a point in which the degradation rate of the object to be evaluated is faster than a predetermined standard, calculated from the evaluated degradation level, the past degradation level of the object to be evaluated, and the elapsed time.

13. A deterioration evaluation system according to any one of claims 1 to 12, comprising a correction means for correcting the color value of the area to be evaluated in the road image according to the color value of a reference object captured in the image by the camera, wherein the evaluation means evaluates the degree of deterioration of the area to be evaluated based on the analysis results using the corrected color value.

14. The deterioration evaluation system according to claim 13, wherein the reference object is a road marking visible in the road image.

15. The degradation evaluation system according to any one of claims 1 to 14, wherein the evaluation means targets the region of two chromatic colors in which the difference in the change characteristics of the color values ​​corresponding to the degree of degradation is the largest.

16. The degradation evaluation system according to any one of claims 1 to 15, wherein the evaluation means targets a color region specified by the user for analysis.

17. The degradation evaluation system according to any one of claims 1 to 16, wherein the evaluation means targets an area specified by the user for analysis.

18. The deterioration evaluation system according to any one of claims 1 to 17, wherein the object to be evaluated is a road sign.

19. A deterioration evaluation method comprising: acquiring a road image captured by a camera mounted on a mobile body; recognizing an object to be evaluated from the road image; identifying multiple regions in the road image within the area of ​​the object to be evaluated that have different original colors; analyzing the relationship between the color in the road image and the original color using the color in the road image of each of the identified multiple regions and the color change characteristics defined for each original color; evaluating the degree of deterioration of the object to be evaluated based on the analysis results; and outputting the evaluated degree of deterioration.

20. A non-temporary recording medium that records a program causing a computer to execute a process that acquires a road image captured by a camera mounted on a mobile body, recognizes an object to be evaluated from the road image, identifies multiple regions in the road image within the area of ​​the object to be evaluated that have different original colors, analyzes the relationship between the color in the road image and the original color using the color in the road image of each of the identified multiple regions and the color change characteristics defined for each original color, evaluates the degree of deterioration of the object to be evaluated based on the analysis results, and outputs the evaluated degree of deterioration.

Images