Imaging distance estimation device, imaging distance estimation method, and program

Abstract

An imaging distance estimation device (3) pertaining to the present disclosure comprises: an input unit (31) that receives input of image data generated by an imaging device (1); a texture region extraction unit (32) that extracts a prescribed texture region from an image indicated by the image data; a feature value calculation unit (33) that calculates a feature value of the texture region; a feature value information storage unit (35) in which feature value information in which a distance and a value relating to the feature value are associated and stored in advance; and an imaging distance estimation unit (36) that calculates a value relating to the feature value, and estimates the imaging distance from the imaging device (1) to the surface of an object corresponding to the texture region as the distance stored in the feature value information storage unit (33), in accordance with the value relating to the feature value.

Description

[Technical field]

[0001] The present disclosure relates to an imaging distance estimation device, an imaging distance estimation method, and a program for determining a deterioration level of a structure. [Background technology]

[0002] It is known to estimate an imaging distance from an imaging device to an object by using an image generated by the imaging device capturing an image of the object, and it is also known to estimate a size of the object based on the imaging distance calculated in this manner.

[0003] For example, Non-Patent Document 1 describes a stereo camera capable of estimating the imaging distance.

[0004] Furthermore, Non-Patent Document 2 describes that the distance to an object shown in an image generated by a stereo camera is indicated by a scale.

[0005] Furthermore, Non-Patent Document 3 describes estimating the dimensions of an object in real space by capturing an image of the object together with an A4 sheet of paper. [Prior art documents] [Non-patent literature]

[0006] [Non-Patent Document 1] "Stereo camera | Product lineup and specifications | Minato Advanced Technologies", [online], [Searched on May 21, 2021], Internet<URL:https: / / www.minatoat.co.jp / stereo#camera / lineup.php> [Non-Patent Document 2] "What is a stereo camera? Basic technology and practical examples - Mobility Solutions - Macnica", [online], [Retrieved May 21, 2021], Internet<URL:https: / / www.macnica.co.jp / business / maas / columns / 134429 / > [Non-Patent Document 3] "Original Stitch announces next-generation AI apparel measurement app "MeasureBot" that instantly estimates clothing measurements using only A4 paper and a smartphone | Original Inc. press release", [online], [searched May 21, 2021], Internet<URL:https: / / prtimes.jp / main / html / rd / p / 000000015.000026235.html> Summary of the Invention [Problem to be solved by the invention]

[0007] However, the techniques described in Non-Patent Documents 1 and 2 require the use of a stereo camera having two cameras, and the technique described in Non-Patent Document 3 requires the preparation of a reference member that is imaged together with an object whose dimensions are to be estimated. In other words, with the conventional techniques, it is not easy to estimate the imaging distance from the imaging device to the object.

[0008] In view of the above circumstances, an object of the present disclosure is to provide an imaging distance estimation device, an imaging distance estimation method, and a program that can easily estimate an imaging distance from an imaging device to an object. [Means for solving the problem]

[0009] In order to solve the above problem, an imaging distance estimation device according to the present disclosure includes an input unit that accepts input of image data generated by an imaging device, a texture area extraction unit that extracts a predetermined texture area from an image represented by the image data, a feature amount calculation unit that calculates a feature amount of the texture area, a feature amount information storage unit that stores in advance feature amount information in which values ​​related to the feature amount are associated with distances, and an imaging distance estimation unit that calculates a value related to the feature amount of the texture area and estimates an imaging distance from the imaging device to a surface of an object corresponding to the texture area as the distance stored in the feature amount information storage unit in response to the value related to the feature amount of the texture area.

[0010] In addition, in order to solve the above-mentioned problems, an imaging distance estimation method according to the present disclosure is an imaging distance estimation method executed by an imaging distance estimation device having a feature information storage unit that stores feature information in which values ​​related to features correspond to distances, and includes the steps of accepting input of image data generated by the imaging device, extracting a predetermined texture region from an image represented by the image data, calculating a feature of the texture region, and calculating a value related to the feature of the texture region, and estimating the imaging distance from the imaging device to the surface of an object corresponding to the texture region as the distance stored in the feature information storage unit, corresponding to the value related to the feature of the texture region.

[0011] In order to solve the above problem, a program according to the present disclosure causes a computer to function as the imaging distance estimation device described above. Effect of the Invention

[0012] According to the imaging distance estimation device, imaging distance estimation method, and program of the present disclosure, the imaging distance from the imaging device to an object can be easily estimated. [Brief description of the drawings]

[0013] [Figure 1]1 is a schematic diagram of an imaging distance estimation system according to a first embodiment. [Diagram 2] 2 is a diagram showing an example of a positional relationship between the imaging device and an object shown in FIG. 1. [Figure 3A] 2A to 2C are diagrams illustrating an example of a state in which the imaging device illustrated in FIG. 1 captures images of an object at different imaging distances. [Figure 3B] 1. FIG. 4 is a diagram showing another example of a state in which the imaging device shown in FIG. 1 captures an image of an object at different imaging distances. [Figure 4A] 2 is a diagram showing an example of a texture region in an image input received by the imaging distance estimation device shown in FIG. 1. [Figure 4B] FIG. 4B is a diagram showing an example of dividing the texture region shown in FIG. 4A. [Figure 4C] FIG. 4B is a diagram showing an example in which the texture region shown in FIG. 4A is reduced. [Diagram 5] 11 is a diagram illustrating an example of the frequency of feature amounts in a texture region according to an imaging distance. FIG. [Figure 6] 13 is a diagram showing an example of a cumulative value of the frequency of feature amounts in a texture region according to an imaging distance; FIG. [Figure 7] 4 is a flowchart showing an example of an operation for storing feature amount information in the imaging distance estimation device shown in FIG. [Figure 8] 4 is a flowchart showing an example of an operation for estimating an imaging distance in the imaging distance estimation device shown in FIG. [Figure 9] FIG. 11 is a schematic diagram of an imaging distance estimation system according to a second embodiment. [Figure 10] 10 is a diagram showing an example of the positional relationship between the imaging device shown in FIG. 9 and an object having a deteriorated portion on its surface. [Figure 11] 10 is a flowchart showing an example of an operation for estimating an imaging distance in the imaging distance estimation device shown in FIG. [Figure 12] FIG. 2 is a hardware block diagram of the imaging distance estimation device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] The overall configuration of the first embodiment will be described with reference to Fig. 1. Fig. 1 is a schematic diagram of an imaging distance estimation system 100 according to this embodiment.

[0015] 1, an imaging distance estimation system 100 according to the first embodiment includes an imaging device 1, an image data storage device 2, an imaging distance estimation device 3, and an estimated information storage device 4. The image data storage device 2 communicates with the imaging device 1 via a communication network. The imaging distance estimation device 3 communicates with the image data storage device 2 and the estimated information storage device 4 via the communication network. The imaging distance estimation device 3 may also communicate with the imaging device 1 via the communication network.

[0016] <Configuration of imaging device> The imaging device 1 is composed of a camera having an optical element, an imaging element, and the like. As shown in FIG. 2, the imaging device 1 is disposed so that at least a part of the surface of the object OB is included in the imaging range. In FIG. 2, the distance from the imaging device 1 to the surface of the object OB is indicated by L. The imaging device 1 captures an image of the object OB and generates an image showing an image of the object OB. In this embodiment, the imaging unit 11 captures an image of the object OB having a pattern formed on its surface and generates image data showing an image including a texture. The object OB can be, for example, a structure such as a building. In addition, when the object OB is a building provided along a road, the imaging device 1 may be mounted on a vehicle traveling on the road.

[0017] The surface of the object OB may be made of metal, wood, etc. The pattern formed on the surface of the object OB may be a pattern formed on a flat surface, a pattern formed by concaves and convexes, or a shadow caused by concaves and convexes. The texture is a portion of an image that corresponds to the pattern formed on the surface of the object OB. Hereinafter, an area in an image where the texture is shown is referred to as a "texture area."

[0018] The imaging device 1 can generate a plurality of images by capturing images of the same object OB from different distances.

[0019] In the example shown in Fig. 3A, the imaging device 1 captures images of different portions of the same object OB having substantially the same surface from different distances. In the example shown in Fig. 3A, the imaging device 1 captures an image of a first portion of the object OB at a position distanced by a distance L11 from the first portion, captures an image of a second portion of the object OB at a position distanced by a distance L12 from the second portion, and captures an image of a third portion of the object OB at a position distanced by a distance L13 from the third portion.

[0020] In the example shown in Fig. 3B, the imaging device 1 generates a plurality of images by capturing images of the same part of the same object OB from different distances. In the example shown in Fig. 3B, the imaging device 1 captures images of the same part of the object OB at positions distant from the object OB by distances L21, L22, and L23.

[0021] The imaging device 1 further includes a communication interface and transmits image data to the image data storage device 2. As described above, when the imaging device 1 generates a plurality of images, it transmits a plurality of image data indicating the plurality of images, respectively, to the image data storage device 2. For the communication interface, standards such as Ethernet (registered trademark), FDDI (Fiber Distributed Data Interface), and Wi-Fi (registered trademark) may be used. The imaging device 1 may also transmit image data to the imaging distance estimation device 3.

[0022] <Image data storage device> The image data storage device 2 is configured by a computer having a memory, a communication interface, etc. It receives the image data transmitted from the imaging device 1 and stores the image data.

[0023] <Configuration of Imaging Distance Estimation Device> The imaging distance estimation device 3 may be a terminal device such as a PC (personal computer) or a tablet, or may be a computer device configured integrally with at least one of the imaging device 1 and the image data storage device 2 described above.

[0024] The imaging distance estimation device 3 includes an input unit 31 , a texture region extraction unit 32 , a feature amount calculation unit 33 , a feature amount comparison unit 34 , a feature amount information storage unit 35 , an imaging distance estimation unit 36 ​​, and an output unit 37 .

[0025] The input unit 31 may be configured by an input interface that accepts input of information, or may be configured by a communication interface that receives information. The texture region extraction unit 32, the feature amount calculation unit 33, the feature amount comparison unit 34, and the imaging distance estimation unit 36 ​​constitute a control unit (controller). The control unit may be configured by dedicated hardware such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field-Programmable Gate Array), or may be configured by a processor, or may be configured by including both. The feature amount information storage unit 35 is configured by memories such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), an EEPROM (Electrically Erasable Programmable Read-Only Memory), a ROM (Read-Only Memory), and a RAM (Random Access Memory). The output unit 37 may be configured by an output interface that outputs information, or may be configured by a communication interface that transmits information.

[0026] The input unit 31 accepts input of image data including texture. The input unit 31 can accept image data and distance information in advance. The distance information is information indicating the distance from the surface of an object OB having a pattern corresponding to the texture included in the image indicated by the image data to the imaging device 1. Here, "in advance" refers to the timing at which processing for configuring the feature amount information storage unit 35 is executed before the input of image data whose distance information is unknown is accepted by the input unit 31. The input unit 31 can also accept input of image data whose distance to the object OB is unknown without distance information.

[0027] The input unit 31 may accept input of image data stored in the image data storage device 2. The input unit 31 may accept input of image data representing an image generated by the imaging device 1, without going through the image data storage device 2.

[0028] When the image representing the image data generated by the imaging device 1 is a moving image, the input unit 31 accepts input of each of a plurality of still images constituting the moving image. Note that, hereinafter, a still image will simply be referred to as an "image".

[0029] As shown in FIG. 4A, the texture region extraction unit 32 extracts an image IM represented by the image data. 0 From the texture area IM 1 The texture region extraction unit 32 can extract a texture region in advance from an image represented by image data the input of which is accepted in advance by the input unit 31 together with distance information. The texture region extraction unit 32 can also extract a predetermined texture region from an image represented by image data the input of which is accepted in advance by the input unit 31 without distance information. The predetermined texture region is a texture region that corresponds to the same surface of the object OB as the texture region extracted in advance by the texture region extraction unit 32.

[0030] Specifically, the texture region extraction unit 32 can extract the texture region using any method such as deep learning, image processing, etc. This allows each functional unit described below to perform each process only on the texture region of the image, rather than on the entire image, thereby reducing the processing load.

[0031] Furthermore, the texture region extraction unit 32 extracts a texture region IM from the image as shown in FIG. 1 Small area IM 2 In a configuration in which the texture region extraction unit 32 divides the texture region extracted from the image, each functional unit described below may process one of the divided regions. In addition, each functional unit may process each of the divided regions, and further calculate statistics (e.g., average value, median value) of the values ​​calculated by the processing. In this way, when there is a bias in the degree to which patterns, unevenness, and shading are applied depending on the parts of the texture region, it is possible to suppress errors in the imaging distance caused by the bias.

[0032] Furthermore, the texture region extraction unit 32 may change the size of the texture region extracted from the image. In a configuration in which the texture region extraction unit 32 changes the size, as shown in FIG. 4C, the texture region extraction unit 32 changes the size of the texture region IM extracted from the image. 1 Reduce the size of the IM area 3 This reduces the processing load of each functional unit described below.

[0033] The feature amount calculation unit 33 calculates the feature amount of the texture region. The texture region extraction unit 32 can calculate the feature amount of a texture region extracted from an image represented by image data that has been received in advance together with distance information by the input unit 31. The texture region extraction unit 32 can also calculate the feature amount of a predetermined texture region extracted from an image represented by image data without distance information.

[0034] The feature amount in this embodiment is an amount calculated by any method based on the luminance value of each pixel constituting an image. For example, the feature amount can be an amount based on a GLCM (Gray-Level Co-occurrence Matrix) calculated based on the luminance value of each pixel. More specifically, the feature amount can be Contrast, Dissimilarity, or Angular Second Moment (ASM) calculated based on the GLCM, as shown in Equations (1) to (3), respectively. Here, i is the pixel number of the central pixel, j is the pixel number of the neighboring pixel, and P is a matrix calculated by analysis of the GLCM.

[0035]

number

[0036]

number

[0037]

number

[0038] FIG. 5 shows the frequency of the feature calculated in advance by the feature calculation unit 33 for each distance shown in the distance information. In the example shown in FIG. 5, the feature is dissimilarity. As shown in FIG. 5, in a certain range (in the example of FIG. 5, the range in which the feature is greater than or equal to x1 and less than or equal to x2), there is a certain correlation between the distance and the frequency of the feature. Specifically, in the range in which the feature is greater than or equal to x1 and less than or equal to x2, the longer the imaging distance, the higher the frequency of the feature. In this example, the feature is dissimilarity, but the feature is not limited to dissimilarity and may be contrast or ASM. Furthermore, the image used in this example is an image generated by imaging the surface of an object OB made of concrete, and as a result, x1=1 and x2=2.5, but x1 and x2 may take different values ​​depending on the surface of the imaged object OB and the type of the feature.

[0039] The feature amount comparison unit 34 calculates a value relating to the feature amount having a certain correlation with the distance, and stores feature amount information in which the distance and the value relating to the feature amount are associated with each other in the feature amount information storage unit 35. In one example, the value relating to the feature amount is a cumulative value (integral value) of the frequency of the feature amount.

[0040] Specifically, the feature quantity comparison unit 34 first extracts a range of feature quantities in which there is a certain correlation between distance and change in frequency of the feature quantity by any method. In the example shown in Fig. 5, the feature quantity comparison unit 34 extracts a range of feature quantities from x1 to x2 inclusive, which is a range in which the frequency of the feature quantity increases as the distance increases. The feature quantity comparison unit 34 may set the feature quantity with the maximum frequency corresponding to the longest distance of 2000 mm as x2.

[0041] Then, the feature quantity comparison unit 34 calculates a value related to the feature quantity in the extracted range. In the example shown in FIG. 5, the feature quantity comparison unit 34 calculates a cumulative value of the frequency of the feature quantity as a value related to the feature quantity in a range in which the feature quantity is equal to or larger than x1 and equal to or smaller than x2. Note that the feature quantity comparison unit 34 may calculate, as a value related to the feature quantity, another value having a correlation with the distance, instead of a cumulative value. As an example, the feature quantity comparison unit 34 may calculate, as a value related to the feature quantity, a feature quantity having a maximum frequency. As another example, the feature quantity comparison unit 34 may calculate, as a value related to the feature quantity, a slope of the frequency with respect to the feature quantity. In this example, it is preferable that the feature quantity comparison unit 34 calculates a slope of the frequency with respect to the feature quantity in a range in which there is a certain correlation as described above (in the example of FIG. 5, a range in which the feature quantity is equal to or larger than x1 and equal to or smaller than x2).

[0042] FIG. 6 shows the cumulative value of the frequency of dissimilarity, which is an example of a feature, for each distance shown in the distance information. As shown in FIG. 6, for feature amounts in a certain range (the range between x1 and x2 in the example of FIG. 6), there is a certain correlation between the distance and the cumulative value of the frequency of the feature amount. In the example of FIG. 6, in the range between x1 and x2 in the example of FIG. 6, the longer the distance, the larger the cumulative value of the frequency of the feature amount. Specifically, FIG. 6 shows that the cumulative values ​​of the frequency of the feature amount corresponding to distances of 250 mm, 500 mm, and 750 mm, respectively, are A 1 , A 2 (>A 1 ), and A 3 (>A 3 ) This shows that the longer the distance, the greater the cumulative value of the feature frequency.

[0043] The feature amount information storage unit 35 stores in advance feature amount information in which a value related to a feature amount is associated with a distance. The feature amount information stored by the feature amount information storage unit 35 is information in which a distance indicated by distance information whose input has been accepted in advance is associated with a value related to a feature amount calculated in advance. In other words, the feature amount information is information in which a distance from the imaging device 1 to the surface of the object OB in real space is associated with a value related to a feature amount.

[0044] The imaging distance estimation unit 36 ​​calculates a value related to the feature amount of the texture region. The imaging distance estimation unit 36 ​​estimates the imaging distance from the imaging device to the surface of the object corresponding to the texture region as the distance stored in the feature amount information storage unit 35 in correspondence with the value related to the feature amount of the texture region. Specifically, as described above, the input unit 31 accepts the input of image data without distance information, the texture region extraction unit 32 extracts the texture region, and the feature amount calculation unit 33 calculates the feature amount, and then the imaging distance estimation unit 36 ​​calculates the value related to the feature amount. Then, the imaging distance estimation unit 36 ​​estimates the imaging distance as the distance stored in the feature amount information storage unit 35 in correspondence with the value related to the feature amount.

[0045] The output unit 37 outputs the estimated information including the imaging distance estimated by the imaging distance estimation unit 36 ​​to the estimated information storage device 4. The output unit 37 may also output the estimated information to a display device such as an organic EL (Electro Luminescence) or liquid crystal panel, and in such a configuration, the display device may display the estimated information. The output unit 37 may transmit the estimated information to another device via a communication network.

[0046] <Configuration of Estimated Information Storage Device> The estimated information storage device 4 is configured by a computer having a memory, a communication interface, etc. It receives the input of the estimated information output from the imaging distance estimation device 3 and stores the estimated information.

[0047] <Operation of the Imaging Distance Estimation Device> Here, an operation for storing feature amount information in the imaging distance estimation device 3 according to this embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing an example of an operation for storing feature amount information in the imaging distance estimation device 3 according to this embodiment.

[0048] In step S11, the input unit 31 accepts input of image data and distance information. As described above, the distance information is information indicating the distance from the surface of an object OB having a pattern corresponding to the texture included in the image indicated by the image data to the imaging device 1.

[0049] In step S12, the texture region extraction unit 32 extracts a texture region from the image represented by the image data.

[0050] In step S13, the feature amount calculation unit 33 calculates the feature amount of the texture region.

[0051] In step S14, the feature amount comparison unit 34 calculates a value relating to the feature amount having a certain correlation with the imaging distance.

[0052] In step S15, the feature amount information storage unit 35 stores feature amount information in which the value relating to the feature amount is associated with the distance indicated by the distance information.

[0053] Next, an operation for estimating the imaging distance of the imaging distance estimation device 3 according to this embodiment will be described with reference to Fig. 8. Fig. 8 is a flowchart showing an example of the operation for estimating the imaging distance in the imaging distance estimation device 3 according to the first embodiment. The operation in the imaging distance estimation device 3 described with reference to Fig. 8 corresponds to the imaging distance estimation method of the imaging distance estimation device 3 according to the first embodiment.

[0054] In step S21, the input unit 31 accepts input of image data.

[0055] In step S22, the texture region extraction unit 32 extracts a texture region from the image represented by the image data.

[0056] In step S23, the feature amount calculation unit 33 calculates the feature amount of the texture region.

[0057] In step S24, the imaging distance estimation unit 36 ​​calculates values ​​related to the feature amounts.

[0058] In step S25, the imaging distance estimating unit 36 ​​estimates the imaging distance based on the value related to the feature amount.

[0059] As described above, according to the first embodiment, the imaging distance estimation device 3 extracts a texture region from an image represented by image data and calculates a feature amount of the texture region. Then, the imaging distance estimation device 3 estimates the imaging distance as a distance stored in the feature amount information storage unit 35 in correspondence with a value related to the feature amount of the texture region. This makes it possible to easily estimate the imaging distance from the imaging device 1 to the surface of the object OB without using a stereo camera having two cameras or preparing a reference member that is imaged together with the object OB. In particular, as described above, when the object OB is a building installed along a road and is mounted on a vehicle traveling on the road, the imaging distance estimation device 3 estimates an imaging distance corresponding to the distance from the vehicle to the building, and based on the imaging distance, it becomes possible to contribute to various controls that contribute to safe driving of the vehicle.

[0060] According to the first embodiment, the value related to the feature amount is a cumulative value of the frequency of the feature amount. Therefore, the imaging distance estimation unit 36 ​​can estimate the imaging distance using a cumulative value that is a single value for the distance. In a configuration in which the value related to the feature amount is the frequency of the feature amount, the imaging distance estimation device 3 must estimate the imaging distance by performing a process such as fitting using the frequency of each feature amount, i.e., a plurality of frequencies. Compared to such a configuration, the imaging distance estimation unit 36 ​​of this embodiment can reduce the processing load. As described above, the value related to the feature amount may be a feature amount whose frequency is a local maximum, or may be a slope of the frequency with respect to the feature amount. Both the feature amount whose frequency is a local maximum and the slope of the frequency are a single value with respect to the distance, similar to the cumulative value. Therefore, for the same reason, the imaging distance estimation unit 36 ​​can reduce the processing load in both a configuration in which the value related to the feature amount is a feature amount whose frequency is a local maximum and a configuration in which the value related to the feature amount is a slope of the frequency.

[0061] In the above-described embodiment, the value related to the feature amount is a cumulative value of the frequency of the feature amount, but this is not limited thereto. For example, the value related to the feature amount may be the frequency of the feature amount. In such a configuration, the feature amount information is information in which the distance is associated with the frequency of each feature amount. Furthermore, the imaging distance estimation unit 36 ​​estimates the imaging distance based on the frequency of each feature amount in the texture region extracted from the image indicated by the image data and the feature amount information stored in the feature amount information storage unit 35 in association with each other.

[0062] The overall configuration of the second embodiment will be described with reference to Fig. 9. Fig. 9 is a schematic diagram of an imaging distance estimation system 101 according to this embodiment. The same functional units as those in the first embodiment are given the same reference numerals, and the description thereof will be omitted.

[0063] 9, an imaging distance estimation system 101 according to the second embodiment includes an imaging device 1, an image data storage device 2, an imaging distance estimation device 3-1, and an estimated information storage device 4. The imaging distance estimation device 3-1 communicates with the image data storage device 2 and the estimated information storage device 4 via a communication network. The imaging distance estimation device 3-1 may also communicate with the imaging device 1 via the communication network.

[0064] <Configuration of Imaging Distance Estimation Device> The imaging distance estimation device 3-1 may be a terminal device such as a PC or a tablet, or may be a computer device configured integrally with at least one of the imaging device 1 and the image data storage device 2. In this embodiment, as shown in Fig. 10, the imaging device 1 generates an image by capturing an image of an object OB having a deteriorated portion DG on its surface.

[0065] The imaging distance estimation device 3-1 includes an input unit 31, a texture region extraction unit 32, a feature amount calculation unit 33, a feature amount comparison unit 34, a feature amount information storage unit 35, an imaging distance estimation unit 36, an output unit 37-1, a degraded region extraction unit 38, and a size estimation unit 39. The degraded region extraction unit 38 and the size estimation unit 39 constitute a control unit. The output unit 37-1 may be constituted by an output interface that outputs information, or may be constituted by a communication interface that transmits information.

[0066] The deteriorated region extraction unit 38 extracts a deteriorated region indicating an image of a deteriorated portion DG on the surface of the object OB from the texture region. The deteriorated region extraction unit 38 can extract a deteriorated region from the texture region by any method. For example, when a structure, which is an example of the object OB, deteriorates, a concrete surface, a steel material, or the like may be exposed around the deteriorated portion DG. For this reason, the deteriorated region extraction unit 38 may extract an image of a concrete surface, a steel material surface, or the like included in the image, and extract a deteriorated region based on the image.

[0067] The size estimation unit 39 estimates the size of the deteriorated portion DG on the surface of the object OB based on the deteriorated region and the imaging distance. The size estimation unit 39 may estimate the area of ​​the deteriorated portion DG, or may estimate the length of the deteriorated portion DG in a predetermined direction.

[0068] In one example, when the imaging distance is calculated by the imaging distance estimation unit 36, the dimension estimation unit 39 calculates the area of ​​the subject at the imaging distance from the imaging device 1 (real space unit area) corresponding to the unit area of ​​the image. Then, the dimension estimation unit 39 estimates the area of ​​the degraded portion DG of the object OB in real space by multiplying the area of ​​the degraded region extracted by the degraded region extraction unit 38 by the real space unit area.

[0069] In another example, when the imaging distance is calculated by the imaging distance estimation unit 36, the dimension estimation unit 39 calculates the length (real space unit length) of the subject at the imaging distance from the imaging device 1, which corresponds to the unit length of the image. Then, the dimension estimation unit 39 estimates the length in the predetermined direction of the degraded portion DG of the object OB in real space by multiplying the length in the predetermined direction of the degraded region extracted by the degraded region extraction unit 38 by the real space unit length.

[0070] The output unit 37-1 outputs estimated information including the dimensions of the deteriorated portion DG on the surface of the object OB estimated by the dimension estimation unit 39. The output unit 37-1 may output estimated information including the dimensions and the imaging distance, or may output estimated information further including an image of the object OB.

[0071] <Operation of the Imaging Distance Estimation Device> The operation for storing feature amount information in the imaging distance estimation device 3-1 according to the second embodiment is similar to the operation for storing feature amount information in the imaging distance estimation device 3 according to the first embodiment.

[0072] Here, an operation for estimating the imaging distance in the imaging distance estimation device 3-1 according to the second embodiment will be described with reference to Fig. 11. Fig. 11 is a flowchart showing an example of the operation for estimating the imaging distance in the imaging distance estimation device 3-1 according to the present embodiment. The operation in the imaging distance estimation device 3-1 described with reference to Fig. 11 corresponds to the imaging distance estimation method of the imaging distance estimation device 3-1 according to the second embodiment.

[0073] In step S31, the input unit 31 accepts input of image data.

[0074] In step S32, the texture region extraction unit 32 extracts a texture region from the image represented by the image data.

[0075] In step S33, the degraded region extraction unit 38 extracts a degraded region from the texture region.

[0076] In step S34, the feature amount calculation unit 33 calculates the feature amount of the texture region.

[0077] In step S35, the imaging distance estimation unit 36 ​​calculates values ​​related to the feature amounts.

[0078] In step S36, the imaging distance estimating unit 36 ​​estimates the imaging distance based on the value related to the feature amount.

[0079] In step S37, the size estimation unit 39 estimates the size of the deteriorated portion DG on the surface of the object OB based on the deteriorated region and the imaging distance.

[0080] The process of step S33 may be executed after any of steps S34 to S36, rather than before step S34.

[0081] As described above, according to the second embodiment, the imaging distance estimation device 3-1 extracts a deteriorated area showing an image of the deteriorated portion DG on the surface of the object OB, and estimates the size of the deteriorated portion DG on the surface of the object OB based on the deteriorated area and the imaging distance. This allows, for example, an inspector to recognize the deterioration state of the object OB without approaching the deteriorated portion DG on the surface of the object OB being inspected.

[0082] <Program> The above-mentioned imaging distance estimation devices 3 and 3-1 can be realized by a computer 102. A program for causing the imaging distance estimation devices 3 and 3-1 to function may be provided. The program may be stored in a storage medium or provided through a network. FIG. 12 is a block diagram showing a schematic configuration of a computer 102 functioning as each of the imaging distance estimation devices 3 and 3-1. Here, the computer 102 may be a general-purpose computer, a dedicated computer, a workstation, a PC (Personal Computer), an electronic notepad, or the like. The program instructions may be program code, code segments, or the like for performing necessary tasks.

[0083] 12, the computer 102 includes a processor 110, a read only memory (ROM) 120, a random access memory (RAM) 130, a storage 140, an input unit 150, a display unit 160, and a communication interface (I / F) 170. Each component is connected to each other via a bus 180 so as to be able to communicate with each other. The processor 110 is specifically a central processing unit (CPU), a micro processing unit (MPU), a graphics processing unit (GPU), a digital signal processor (DSP), a system on a chip (SoC), or the like, and may be composed of multiple processors of the same type or different types.

[0084] The processor 110 controls each component and executes various arithmetic processing. That is, the processor 110 reads a program from the ROM 120 or the storage 140, and executes the program using the RAM 130 as a working area. The processor 110 controls each component and executes various arithmetic processing according to the program stored in the ROM 120 or the storage 140. In this embodiment, the program according to the present disclosure is stored in the ROM 120 or the storage 140.

[0085] The program may be stored in a storage medium readable by the computer 102. By using such a storage medium, the program can be installed in the computer 102. Here, the storage medium in which the program is stored may be a non-transitory storage medium. The non-transitory storage medium is not particularly limited, and may be, for example, a CD-ROM, a DVD-ROM, or a USB (Universal Serial Bus) memory. In addition, the program may be in a form that is downloaded from an external device via a network.

[0086] The ROM 120 stores various programs and various data. The RAM 130 temporarily stores programs or data as a working area. The storage 140 is configured with an HDD (Hard Disk Drive) or an SSD (Solid State Drive) and stores various programs including an operating system and various data.

[0087] The input unit 150 includes one or more input interfaces that receive an input operation from a user and acquire information based on the user's operation. For example, the input unit 150 is a pointing device, a keyboard, a mouse, etc., but is not limited to these.

[0088] The display unit 160 includes one or more output interfaces that output information. For example, the display unit 160 is a display that outputs information as a video or a speaker that outputs information as a sound, but is not limited to these. Note that, if the display unit 160 is a touch panel type display, it also functions as the input unit 150.

[0089] The communication interface 170 is an interface for communicating with an external device.

[0090] The following supplementary notes are further disclosed regarding the above embodiment.

[0091] (Additional note 1) a feature amount information storage unit storing feature amount information in which a value relating to a feature amount is associated with a distance; an input unit that accepts input of image data generated by an imaging device; a control unit that extracts a predetermined texture region from an image represented by the image data and calculates a feature amount of the texture region; A feature amount information storage unit that stores feature amount information in which a value related to the feature amount is associated with a distance in advance. the control unit calculates a value related to the feature amount of the texture region, and estimates an imaging distance from the imaging device to a surface of an object corresponding to the texture region as a distance stored in the feature amount information storage unit in correspondence with the value related to the feature amount. (Additional note 2) the input unit accepts input of image data generated in advance by capturing an image of the object and distance information indicating the distance; The control unit is Extracting a texture region from an image represented by the image data in advance; A feature amount of the texture region is calculated in advance; 2. The imaging distance estimation device according to claim 1, wherein the feature amount information is information in which a distance indicated by distance information previously received as an input is associated with a value related to the feature amount calculated in advance. (Additional note 3) 3. The imaging distance estimation device according to claim 1, wherein the value related to the feature amount is a cumulative value of a frequency of the feature amount. (Additional note 4) The control unit is extracting a degraded region from the texture region, the degraded region being indicative of an image of a degraded portion on the surface of the object; 4. The imaging distance estimation device according to claim 1, further comprising: estimating a dimension of a deteriorated portion on a surface of the object based on the deteriorated region and the imaging distance. (Additional note 5) An imaging distance estimation method executed by an imaging distance estimation device having a feature amount information storage unit that stores feature amount information in which a value related to a feature amount is associated with a distance, the method comprising: receiving input of image data generated by an imaging device; extracting a predetermined texture region from an image represented by said image data; calculating a feature amount of the texture region; a step of estimating an imaging distance from the imaging device to a surface of an object corresponding to the texture region as a distance stored in the feature amount information storage unit in correspondence with a value related to a feature amount of the texture region; An imaging distance estimation method comprising: (Additional note 6) A non-transitory storage medium storing a program executable by a computer, the program causing the computer to function as the imaging distance estimation device according to any one of claims 1 to 4.

[0092] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0093] Although the above-mentioned embodiment has been described as a representative example, it is obvious to those skilled in the art that many modifications and substitutions can be made within the spirit and scope of the present disclosure. Therefore, the present invention should not be interpreted as being limited by the above-mentioned embodiment, and various modifications or changes can be made without departing from the scope of the claims. For example, it is possible to combine multiple building blocks shown in the configuration diagram of the embodiment into one, or to divide one building block. [Explanation of symbols]

[0094] 1. Imaging device 2. Image data storage device 3, 3-1 Imaging distance estimation device 4. Estimated information storage device 31 Input section 32 Texture region extraction unit 33 Feature Calculation Unit 34 Feature Comparison Unit 35 Feature information storage section 36 Imaging distance estimation unit 37, 37-1 Output section 38 Deterioration area extraction part 39 Dimension Estimation Section 100, 101 Imaging distance estimation system 102 Computer 110 Processor 120 ROM 130 RAM 140 Storage 150 Input section 160 Output section 170 Communication Interface 180 Bus

Claims

1. an input unit that accepts input of image data generated by an imaging device; a texture region extraction unit that extracts a predetermined texture region from an image represented by the image data; a feature amount calculation unit for calculating a feature amount of the texture region; a feature amount comparison unit that extracts a partial range of the feature amount in which there is a certain correlation between the distance to the surface of the object corresponding to the texture region and the frequency of the feature amount in a relationship between the feature amount and the frequency of the feature amount, and calculates a value related to the feature amount in the extracted range; a feature amount information storage unit that stores in advance feature amount information in which values ​​related to the feature amount are associated with the distance; an imaging distance estimation unit that calculates a value related to the feature amount of the texture region and estimates an imaging distance from the imaging device to a surface of an object corresponding to the texture region as a distance stored in the feature amount information storage unit in correspondence with the value related to the feature amount of the texture region; An imaging distance estimation device comprising:

2. the input unit accepts input of image data generated in advance by capturing an image of the object and distance information indicating the distance; The texture region extraction unit extracts a texture region from an image represented by the image data in advance, The feature amount calculation unit calculates the feature amount of the texture region in advance, The imaging distance estimation device according to claim 1 , wherein the feature amount information is information in which a distance indicated by distance information previously received as an input is associated with a value related to the feature amount calculated in advance.

3. The imaging distance estimation device according to claim 1 , wherein the value relating to the feature amount is a cumulative value of the frequency of the feature amount.

4. a deteriorated region extraction unit that extracts a deteriorated region indicating an image of a deteriorated portion on a surface of the object from the texture region; a size estimation unit that estimates a size of a deteriorated portion on a surface of the object based on the deteriorated area and the imaging distance; The imaging distance estimation device according to claim 1 , further comprising:

5. An imaging distance estimation method executed by an imaging distance estimation device having a feature amount information storage unit that stores feature amount information in which a value related to a feature amount is associated with a distance, the method comprising: receiving input of image data generated by an imaging device; extracting a predetermined texture region from an image represented by said image data; calculating a feature amount of the texture region; extracting a partial range of the feature amount in which there is a certain correlation between the distance to the surface of the object corresponding to the texture region and the frequency of the feature amount in a relationship between the feature amount and the frequency of the feature amount, and calculating a value related to the feature amount in the extracted range; calculating a value related to the feature amount of the texture region, and estimating an imaging distance from the imaging device to a surface of an object corresponding to the texture region as the distance stored in the feature amount information storage unit in correspondence with the value related to the feature amount of the texture region; An imaging distance estimation method comprising:

6. A program for causing a computer to function as the imaging distance estimation device according to claim 1 .

Images