Aggregate particle size distribution estimation system

Abstract

To provide an aggregate granularity distribution estimation system which can reduce the burden on a worker who performs measurement of the granularity distribution of an aggregate to be mixed when creating concrete and easily obtain the granularity distribution of the aggregate.SOLUTION: An aggregate granularity distribution estimation system for estimating the granularity distribution of an aggregate to be mixed when creating concrete comprises: a shape feature extraction unit which extracts a shape feature amount obtained from at least the contour length, contour area and circularity of an aggregate as a feature amount of each of the photographed aggregates from an aggregate surface image being a photographed image obtained by photographing the surfaces of the accumulated aggregates; a color feature extraction unit which extracts a color feature amount obtained from at least the gradient, hue, saturation and brightness of a color component of the aggregate as a feature amount of each of the photographed aggregates from the aggregate surface image; and a granularity distribution estimation unit which estimates the granularity distribution of the aggregate by using a prescribed machine learning model with the shape feature amount and the color feature amount input thereto.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an aggregate particle size distribution estimation system. [Background technology]

[0002] Conventionally, when creating concrete structures, aggregate is mixed into ready-mixed concrete to reduce shrinkage and cracking that occurs when the concrete hardens. In other words, concrete is composed of four materials: water, cement, coarse aggregate (gravel), and fine aggregate (sand), and quality control of the aggregate, which accounts for the majority of the weight, is important. The particle size distribution of the coarse aggregate mixed into concrete varies depending on the use, purpose, and strength of the concrete, and the type of concrete. For this reason, the grading of coarse aggregate and fine aggregate is used as an important parameter in calculating the strength of concrete structures.

[0003] On the other hand, aggregates are sieved in an attempt to make the particle size of the aggregate constant, but even aggregates sieved to the same particle size (particle diameter of the aggregate) have a particle size distribution (distribution of particle diameters of aggregate particle groups) in which aggregates of different particle sizes are mixed together. For this reason, the method for measuring the particle size of aggregates is specified in the Japanese Industrial Standards (JIS A1102:2014) as the "Aggregate Sieving Test Method." However, the above-mentioned "aggregate sieving test method" places a heavy burden on the worker conducting the test, and it is difficult to carry out the test frequently.

[0004] Therefore, in order to reduce the burden on the worker compared to the "aggregate sieving test method," there is a system in which coarse aggregate is spread in a single layer on a measuring plate, and the captured image of the aggregate is analyzed to measure the particle size distribution (see, for example, Patent Document 1). There is also a system that scatters coarse aggregate onto a belt conveyor, captures images of the coarse aggregate on the belt conveyor, extracts the contours of each of the captured aggregates, and measures the particle size distribution (see, for example, Patent Document 2).

[0005] There is also a system that measures particle size distribution by scattering coarse aggregate in a cylindrical shape and allowing it to fall, capturing images of the falling coarse aggregate, extracting the outline of each of the captured coarse aggregates, and measuring the particle size of each of the aggregates using these outlines (see, for example, Patent Document 3). There is a system that measures particle size by converting the shape of each fine aggregate into an equivalent circle by image processing a captured image of a microphotograph of the fine aggregate (see, for example, Non-Patent Document 1). [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Laid-Open No. 2008-268051 [Patent Document 2] Japanese Patent Application Laid-Open No. 2003-010726 [Patent Document 3] Japanese Patent Application Laid-Open No. 2016-070714 [Non-patent literature]

[0007] [Non-Patent Document 1] Ito, K., Tsujimoto, K., Suzuki, K., Tsuji, Y., "Development of a simple inspection method for fine aggregate particle size using an image processing system," Cement Science and Concrete Technology. 63, 227-232, 2009. Summary of the Invention [Problem to be solved by the invention]

[0008] However, unlike the "aggregate sieving test method," each of the above-mentioned prior arts can reduce the burden on the worker conducting the test, but each requires special equipment when imaging the aggregate and analyzing the particle size distribution. For this reason, it is difficult to install the above-mentioned equipment at construction sites where concrete structures are actually created, or at ready-mixed concrete (ready-mixed concrete) manufacturing plants where concrete is produced.

[0009] The present invention has been made in consideration of the above circumstances, and aims to provide an aggregate particle size distribution estimation system that reduces the burden on workers who measure the particle size distribution of aggregates (coarse aggregate, fine aggregate) mixed in concrete when preparing it, and that can easily determine the particle size distribution of the aggregate. [Means for solving the problem]

[0010] In order to solve the above-mentioned problems, the aggregate particle size distribution estimation system of the present invention is an aggregate particle size distribution estimation system that estimates the particle size distribution of aggregate (coarse aggregate or fine aggregate) mixed in when producing concrete, and is characterized by comprising: a shape feature extraction unit that extracts shape feature quantities calculated from at least the contour length, contour area, and circularity of the aggregate as feature quantities of each of the captured aggregate from an aggregate surface image, which is an image obtained by capturing an image of the surface of piled aggregate; a color feature extraction unit that extracts color feature quantities calculated from at least the gradient, hue, saturation, and lightness of the color components of the aggregate as feature quantities of each of the captured aggregate from the aggregate surface image; and a particle size distribution estimation unit that receives the shape feature quantities and the color feature quantities and estimates the particle size distribution of the aggregate using a predetermined machine learning model. [Effects of the Invention]

[0011] According to the present invention, it is possible to provide an aggregate particle size distribution estimation system that reduces the burden on workers who measure the particle size distribution of aggregates (coarse aggregate, fine aggregate) to be mixed in concrete when preparing it, and that can easily determine the particle size distribution of the aggregate. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a block diagram showing an example of the configuration of an aggregate particle size distribution estimation system according to an embodiment of the present invention. [Figure 2] 10A and 10B are diagrams illustrating the capturing of an aggregate surface image in this embodiment. [Figure 3] FIG. 2 is a diagram showing an example of the structure of a feature table written and stored in a feature storage unit 19 in this embodiment. [Figure 4] 10 is a diagram showing an example of the configuration of a table showing the correspondence between aggregate image identification information and particle size distribution of coarse aggregate. FIG. [Figure 5] 10 is a flowchart showing an example of the operation of a process for classifying the particle size distribution of coarse aggregate, the particle size distribution of which is unknown, into each of known particle size distributions, performed by the aggregate particle size distribution estimation system according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0013] Fig. 1 is a block diagram showing an example of the configuration of an aggregate particle-size distribution estimation system according to one embodiment of the present invention. In Fig. 1, aggregate particle-size distribution estimation system 10 includes a data input / output unit 11, a captured image preprocessing unit 12, a shape feature extraction unit 13, a color feature extraction unit 14, a machine learning model generation unit 15, a particle-size distribution estimation unit 16, a feature importance evaluation unit 17, an image data storage unit 18, a feature storage unit 19, a machine learning model storage unit 20, and a training data storage unit 21. The following description will be given taking coarse aggregate as an example of aggregate, but similar processing can be performed for fine aggregate as well.

[0014] The data input / output unit 11 transmits and receives data to and from an external device. The data input / output unit 11 also writes and stores aggregate surface image data, which is an image of coarse aggregate captured from an external device, in the image data storage unit 18 after adding aggregate surface image identification information. The aggregate surface image is captured in a closed space, such as a dark box, that blocks external light.

[0015] FIG. 2 is a diagram for explaining how to capture an aggregate surface image in this embodiment. Fig. 2(a) is a diagram showing how coarse aggregate, which is the object to be imaged, is piled up in a container with an open top, such as a bucket, and the surface of the piled coarse aggregate is imaged to obtain an image 101. Fig. 2(b) shows how the acquired image 101 is trimmed so that the image area is limited to the surface of the coarse aggregate, and this trimming result is an aggregate surface image 102.

[0016] 2(c) shows an example of a method for capturing an aggregate surface image. A bucket 201 containing a pile of coarse aggregate 202 is placed in a container 200, such as a dark box that blocks external light. The surface of the piled coarse aggregate 202 is then captured by an imaging device 210 at the timing when a flash 211 is emitted. This makes it possible to keep the imaging environment for capturing aggregate surface images constant, and to capture multiple aggregate surface images under the same conditions. In this embodiment, the camera parameters of the imaging device are also the same when capturing each aggregate surface image.

[0017] 1, the captured image preprocessing unit 12 performs the trimming process described above to obtain an aggregate surface image, and also performs processing such as erasing the shadows of other coarse aggregates in the image region of each coarse aggregate in the aggregate surface image. Then, the captured image preprocessing unit 12 writes and stores the processed aggregate surface image in the image data storage unit 18 in association with the aggregate surface image identification information.

[0018] The shape feature extraction unit 13 performs a process of extracting the contours of each of the coarse aggregates in the aggregate surface image. The shape feature extraction unit 13 then calculates the perimeter length of each of the extracted contours as a contour length, adds up the contour lengths of all the extracted contours, and acquires a contour length total value, which is the total value of the contour lengths, as one of the shape feature quantities. The shape feature extraction unit 13 also calculates the average value of the contour lengths of each of the contours as the contour length average value, and calculates the standard deviation of the contour lengths of each of the contours as the contour length standard deviation, as shape feature quantities.

[0019] Similarly, shape feature extraction unit 13 calculates the area inside the extracted contour as the contour area, adds up the contour areas of all the extracted contours, and obtains the total contour area value as one of the shape feature quantities. Furthermore, shape feature extraction unit 13 calculates the average value of the contour areas of each contour as the contour area average, and calculates the standard deviation of the contour areas of each contour as the contour area standard deviation, as shape feature quantities.

[0020] The shape feature extraction unit 13 calculates the contour circularity, which is the circularity of the shape of the contour line of the extracted contour, and adds up the contour circularities of all the extracted contours to obtain a contour circularity total value, which is the total value of the contour circularities, as one of the shape feature quantities. Here, the shape feature extraction unit 13 calculates the circularity circ of each contour line of the coarse aggregate using the following equation (1). In this equation (1), area is the contour area of the coarse aggregate, and length is the contour length of the coarse aggregate. circ=4π×area / (length) 2 …(1)

[0021] Furthermore, as shape feature quantities, shape feature extraction unit 13 calculates the average value of the contour circularity of each contour as the contour circularity average value, and calculates the standard deviation of the contour circularity of each contour as the contour circularity standard deviation. Then, shape feature extraction unit 13 writes and stores each of the acquired shape feature quantities in feature quantity storage unit 19.

[0022] The color feature extraction unit 14 extracts color information for each pixel in the aggregate surface image to acquire color feature quantities for the aggregate surface image. For example, the color information may be obtained by calculating the average values of the gradients of the R, G, and B color components of each pixel in the aggregate surface image to acquire the R average value, G average value, and B average value. At this time, the color feature extraction unit 14 calculates a grayscale for each pixel in the aggregate surface image from the R, G, and B color components to acquire the grayscale average value, which is the average value of the grayscales. The color feature extraction unit 14 then writes and stores the acquired R average value, G average value, and B average value in the feature storage unit 19.

[0023] As for color information, the gradients of the color components R, G, B and grayscale are each divided into a plurality of ranges, and for example, if there are 256 gradations, they are classified into eight classes: 0-31, 32-63, 64-95, 96-127, 128-159, 160-191, 192-223, and 224-255. The color feature extraction unit 14 then divides the number of pixels included in each class by the total number of pixels in the aggregate surface image, and sets the division result for each class as the occurrence rate of each class.

[0024] For example, the color feature extraction unit 14 divides the number of pixels in the eight classes of the color component R by the total number of pixels in the aggregate surface image to obtain division values for classes from 0-31 to 224-255, thereby obtaining the occurrence rate of each class of the color component R gradient. The color feature extraction unit 14 also standardizes the occurrence rates so that the maximum and minimum occurrence rates in the eight classes of the color component R become 1 and 0, respectively, and writes and stores each of the obtained occurrence rates of the color component R (the color component R occurrence rate for each of the eight classes) in the feature storage unit 19. The color feature extraction unit 14 also performs the same process as for the color component R on each of the color components G, B, and grayscale, and writes and stores each of the obtained color component G occurrence rate, color component B occurrence rate, and grayscale occurrence rate in the feature storage unit 19.

[0025] Furthermore, the color feature extraction unit 14 calculates the average values of hue H, saturation S, and lightness V in HSV display for each pixel of the aggregate surface image as other color feature quantities, thereby obtaining the average hue value, average saturation value, and average lightness value.The color feature extraction unit 14 then writes and stores the obtained average hue value, average saturation value, and average lightness value in the feature storage unit 19.The color feature extraction unit 14 divides the range of the values of hue H, saturation S, and lightness V into eight classes, similar to gradients, and classifies each pixel into one of the classes.

[0026] For example, the color feature extraction unit 14 converts the numerical values of the hue scale from 0 to 359 indicating the hue H into 256 gradations from 0 to 255, classifies them into eight classes, and, as in the case of gradations, classifies each pixel according to the hue H and divides the number of pixels classified into each class by the total number of pixels in the aggregate surface image.The color feature extraction unit 14 then standardizes the occurrence rates so that the maximum and minimum occurrence rates in the hue H class are 1 and 0, respectively, to obtain standardized hue occurrence rates.The color feature extraction unit 14 writes and stores each of the acquired hue occurrence rates (the hue occurrence rate in each of the eight classes) in the feature storage unit 19.

[0027] Similarly, the color feature extraction unit 14 converts the numerical value from 0% to 100% indicating the saturation S into 256 gradations from 0 to 255, classifies them into eight classes, and, as in the case of gradations, classifies each pixel according to its saturation S and divides the number of pixels classified into each class by the total number of pixels in the aggregate surface image.The color feature extraction unit 14 then standardizes the occurrence rate so that the maximum and minimum occurrence rates in the saturation S class are 1 and 0, respectively, to obtain a standardized saturation occurrence rate.The color feature extraction unit 14 writes and stores each of the acquired saturation occurrence rates (the saturation occurrence rate for each of the eight classes) in the feature storage unit 19.

[0028] The color feature extraction unit 14 also converts the numerical values from 0% to 100% indicating the lightness V into 256 gradations from 0 to 255, classifying them into eight classes, and, as in the case of gradients, classifies each pixel according to its lightness V, and divides the number of pixels classified into each class by the total number of pixels in the aggregate surface image. The color feature extraction unit 14 then standardizes the occurrence rates so that the maximum and minimum occurrence rates in the lightness V classes are 1 and 0, respectively, to obtain standardized lightness occurrence rates. The color feature extraction unit 14 writes each of the acquired lightness occurrence rates (the lightness occurrence rate for each of the eight classes) into the feature amount storage unit 19 and stores them therein.

[0029] 3A and 3B are diagrams showing an example of the structure of a feature table written and stored in the feature storage unit 19 in this embodiment. Fig. 3A shows an example of the structure of a shape feature table, which is one of the feature tables. The shape feature table has columns for each record, as feature groups of shape features, for example, the aggregate image identification information, the total contour length, the average contour length, the standard deviation of contour length, the total contour area, the average contour area, the standard deviation of contour area, the total contour circularity, the average contour circularity, and the standard deviation of contour circularity.

[0030] 3(b) shows an example of the configuration of a color feature table, which is one of the feature tables. The color feature table has columns for each record as a group of color feature values, including the aggregate image identification information, R average value, R color component appearance ratio, G average value, G color component appearance ratio, B average value, B color component appearance ratio, grayscale average value, grayscale appearance ratio, hue average value, hue appearance ratio, saturation average value, saturation appearance ratio, lightness average value, and lightness appearance ratio. Furthermore, each of the R color component appearance ratio, G color component appearance ratio, B color component appearance ratio, grayscale appearance ratio, hue appearance ratio, saturation appearance ratio, and lightness appearance ratio is written in a column as a set of eight numerical values of the appearance ratio for each class.

[0031] Returning to FIG. 1 , the machine learning model generation unit 15 receives the above-described shape feature values and color feature values and generates a machine learning model that outputs an estimated value of the aggregate particle size distribution (hereinafter simply referred to as particle size distribution) of the coarse aggregate. That is, the machine learning model in this embodiment is a classifier that classifies a plurality of particle size distributions. By receiving a set of feature data of each of the shape feature values and color feature values, the machine learning model outputs a confidence level (an estimated value indicating the likelihood, an estimated value p described below) when the particle size distribution of the coarse aggregate captured in the aggregate surface image is classified into each label. For example, in this embodiment, three particle size distributions, particle size distributions #1, #2, and #3, are used as labels. Therefore, the machine learning model outputs a confidence level for each of the particle size distributions #1, #2, and #3, and the particle size distribution with the highest confidence level is estimated to be the most likely to be the particle size distribution of the coarse aggregate captured in the aggregate surface image.

[0032] The machine learning model generation unit 15 captures images of the surface of coarse aggregate with a known particle size distribution and generates a data group for training the machine learning model. In this embodiment, for example, a multilayer perceptron classifier is used as the machine learning model, but any other classifier using a neural network or the like may also be used. In this embodiment, the data group is divided at a predetermined ratio, and for example, 80% of the data in the data group is used as a training data group for learning (training) the machine learning model. The remaining 20% of the data group is used as test data for calculating the accuracy rate of the created machine learning model.

[0033] The machine learning model generation unit 15 also divides the teacher data group into a training data group and a validation data group at a predetermined ratio, and, for example, designates each of 80% of the data in the teacher data group as a training data group used for actual learning (training) of the machine learning model. The machine learning model generation unit 15 then designates each of the remaining 20% of the data in the teacher data group as a validation data group used for verifying the accuracy rate of the machine learning model trained with the data in the training data group. Here, the machine learning model generation unit 15 extracts a portion of data at a predetermined ratio (20%) from the training data group, replaces the same number of teacher data pieces with those in the validation data group, trains the machine learning model with the data in the new training data group after the replacement, and uses the data in the new validation data group to verify the accuracy rate of the machine learning model. The machine learning model generation unit 15 then performs the data replacement operation in each of the training data group and the validation data group a predetermined number of times to train the machine learning model.

[0034] The feature amounts used as training data are written and stored as a training data table in the training data storage unit 21. This training data table has the same configuration as the shape feature amount table and color feature amount table shown in Fig. 3. The training data table stores each of the shape feature amounts and color feature amounts obtained by analyzing training data images, which are images of the surface of coarse aggregates whose particle size distribution is known.

[0035] The feature importance evaluation unit 17 selects either a shape feature or a color feature in the training data used to train the trained model, and evaluates the impact on the confidence level when the data of that feature is swapped between aggregate surface images. For example, the contour length data in the shape feature is randomly shuffled among the aggregate surface image identification information, and the shuffled feature set is input to the trained model. The importance of the contour length as a feature for training the machine learning model is determined based on the level of confidence reduction. By shuffling the feature data in this way for all feature values, the importance of the feature in training the machine learning model can be confirmed. For example, using this result, it is possible to compact the machine learning model by not using feature values with confidence reduction values that are less than a predetermined percentage of the largest confidence reduction value for training the machine learning model. In this embodiment, the feature importance evaluation unit 17 processed the following features to extract the top 10: total contour circularity value, total contour length value, average saturation value, hue appearance rate (gradation 96-127), hue appearance rate (160-191), lightness appearance rate (gradation 192-223), color component B appearance rate (gradation 192-223), average contour length value, color component B appearance rate (gradation 0-31), and hue appearance rate (0-31).

[0036] FIG. 4 is a diagram showing an example of the configuration of a table showing the correspondence between aggregate image identification information and the particle size distribution of coarse aggregate. FIG. 4(a) shows an example of the configuration of the training data information table in the training data storage unit 21. The training data information table has columns for aggregate image identification information, particle size distribution type, and use type for each record. This aggregate image identification information is identification information that individually identifies each aggregate surface image of coarse aggregate with a known particle size distribution used as training data. The particle size distribution indicates the type of particle size distribution of the coarse aggregate from which the aggregate surface image was captured (the type of particle size distribution that serves as a label when training). In this embodiment, for example, three types of particle size distribution are used, and are respectively indicated as particle size distribution #1, particle size distribution #2, and particle size distribution #3. The use type indicates whether each feature of the aggregate surface image, which is training data, is used as data in the training data group or the validation data group, or as test data.

[0037] Fig. 4(b) shows a configuration example of the estimation result table in the feature quantity storage unit 19. In the estimation result table, columns for aggregate imaging image identification information, particle size distribution #1, particle size distribution #2, and particle size distribution #3 are provided for each record. This aggregate imaging image identification information is identification information for individually identifying each aggregate surface imaging image in which the particle size distribution of the coarse aggregate is unknown. The column for particle size distribution #1 shows an estimated value p (for example, 0 < p < 1) indicating the confidence level (likelihood) that the particle size distribution of the coarse aggregate with an unknown particle size distribution, when the feature quantity is input and estimated by the machine learning model, is classified into the labeled particle size distribution #1. Similarly, the column for particle size distribution #2 shows an estimated value p indicating the confidence level that the particle size distribution of the coarse aggregate with an unknown particle size distribution, when the feature quantity is input and estimated by the machine learning model, is classified into the labeled particle size distribution #2. The column for particle size distribution #3 shows an estimated value p indicating the confidence level that the particle size distribution of the coarse aggregate with an unknown particle size distribution, when the feature quantity is input and estimated by the machine learning model, is classified into the labeled particle size distribution #3.

[0038] Fig. 5 is a flowchart showing an operation example of a process for classifying the particle size distribution of a coarse aggregate with an unknown particle size distribution into each of known particle size distributions by the aggregate particle size distribution estimation system according to the present embodiment. In the present embodiment, as an example, a generation process of a machine learning model (classifier) for classifying a coarse aggregate with an unknown particle size distribution into these three types of particle size distributions (labels) and a classification process of classifying a coarse aggregate with an unknown particle size distribution by the generated machine learning model into three types of labels will be described.

[0039] The user deposits coarse aggregates with known particle size distributions in the bucket and, in a closed space where external light is blocked, captures, using an imaging device, an aggregate surface imaging image, which is a surface image of the deposited coarse aggregates to be used as teacher data (step S1). Then, the captured image preprocessing unit 12 performs preprocessing such as trimming the captured aggregate surface imaging image and removing shadows.

[0040] The shape feature extraction unit 13 and the color feature extraction unit 14 extract shape features and color features from each of the aggregate surface images obtained by capturing images of a plurality of coarse aggregates, i.e., coarse aggregates having three types of particle size distributions, and write and store the extracted images in a teacher data table in the teacher data storage unit 21. Here, for example, several hundred images of the aggregate surface are captured for each of the three known particle size distribution types of coarse aggregate, and are acquired as a feature data group of the teacher data (step S2). In addition, the machine learning model generation unit 15 sets 80% of the feature data group in the teacher data table in the teacher data storage unit 21 as teacher data and 20% as test data, and enters these in the usage type column of the teacher data table (steps S3 and S4).

[0041] The machine learning model generation unit 15 sets 80% (i.e., 64% of the data group) of the feature data group (i.e., the teacher data group) in the teacher data table in the teacher data storage unit 21 as a training data group, and 20% (i.e., 16% of the data group) as a verification data group, and enters these in the usage type column of the teacher data table (steps S5 and S6). The machine learning model generation unit 15 then performs learning by adjusting the parameters of the machine learning model (classifier) using data whose use type is the training data group in the training data table in the training data storage unit 21 (steps S7, S8, and S9). At this time, the machine learning model generation unit 15 calculates the accuracy rate of the classification of the machine learning model to be learned using data whose use type is the validation data in the training data table in the training data storage unit 21 (model verification, correct / incorrect determination). The machine learning model generation unit 15 also exchanges the data in the validation data group with a portion of the data in the training data group (e.g., 20% of the training data group), and uses the data in the new training data group after the exchange to re-train the generated machine learning model. This re-training (re-parameter adjustment) of the machine learning model in which the data in the validation data group has been exchanged with the portion of the data in the training data group is performed a predetermined number of times, thereby generating a trained machine learning model for estimating aggregate particle-size distribution (trained model), and writing and storing the model in the machine learning model storage unit 20.

[0042] Furthermore, the machine learning model generation unit 15 calculates the confidence level (correct / incorrect judgment) of the classification of the machine learning model to be trained for the trained model of aggregate particle size distribution estimation (trained machine learning model) as the accuracy rate (steps S10 and S11) using data with the application type of test data in the training data table in the training data storage unit 21. Here, if the accuracy rate of the trained model is low, the machine learning model generation unit 15 may be configured to return to step S3 and train the machine learning model again.

[0043] A user piles coarse aggregate with an unknown particle size distribution into a bucket, and in a closed space shielded from external light, an image of the aggregate surface, which is a surface image of the piled coarse aggregate, is taken by an imaging device (step S12). Then, the captured image preprocessing unit 12 performs preprocessing such as trimming the captured aggregate surface image and removing shadows.

[0044] The shape feature extraction unit 13 and the color feature extraction unit 14 extract shape features and color features from each of the aggregate surface images obtained by capturing coarse aggregate with unknown particle size distribution, and write and store the extracted shape features and color features as a feature data group in a feature table in the feature storage unit 19 in association with the assigned aggregate image identification information (step S13). The particle size distribution estimation unit 16 reads out the trained model from the machine learning model storage unit 20, and also reads out a feature data group from the feature table of the feature storage unit 19. Then, the particle size distribution estimation unit 16 inputs the feature data group into the trained model, and writes and stores the confidence of each output label in the label column in the result table of the feature storage unit 19 (steps S14 and S15).

[0045] According to this embodiment, by inputting shape features and color features extracted from an aggregate surface image, which is a surface image of piled aggregate (e.g., coarse aggregate), to a trained model that has been trained using shape features and color features extracted from an aggregate surface image of aggregate with a known particle size distribution, it is possible to produce concrete without requiring a large-scale particle size distribution measuring device as in the past, reduce the burden on workers who measure the particle size distribution of the aggregate to be mixed in, and easily determine the particle size distribution of the aggregate (coarse aggregate and fine aggregate). Furthermore, according to this embodiment, it is possible to easily estimate the particle size distribution of aggregates (coarse aggregate and fine aggregate) at construction sites or at businesses that manufacture ready-mixed concrete, as described above, which makes it possible to easily ensure (provide) quality control in the construction of concrete structures and traceability of data on aggregate particle size distribution in the construction of concrete structures, thereby preventing rework due to poor quality.

[0046] The particle size distribution of coarse aggregate may be estimated by recording a program for implementing the functions of the aggregate particle size distribution estimation system 10 shown in FIG. 1 on a computer-readable recording medium and loading and executing the program on the recording medium into a computer system. The term "computer system" as used herein includes hardware such as an operating system (OS) and peripheral devices. The term also includes a World Wide Web (WWW) system equipped with a web page environment (or display environment). The term "computer-readable recording medium" refers to portable media such as flexible disks, magneto-optical disks, read-only memories (ROMs), and compact disc-read-only memories (CD-ROMs), as well as storage devices such as hard disks built into computer systems. The term "computer-readable recording medium" also includes devices that retain a program for a certain period of time, such as volatile memory (RAM (Random Access Memory)) within computer systems that function as servers or clients when a program is transmitted via a network such as the Internet or a communication line such as a telephone line.

[0047] The program may also be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by transmission waves in the transmission medium. Here, the "transmission medium" that transmits the program refers to a medium that has the function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line. The program may also be a program that realizes part of the above-mentioned functions. Furthermore, the program may be a so-called differential file (differential program) that can realize the above-mentioned functions in combination with a program already recorded in the computer system. [Explanation of symbols]

[0048] 10...Aggregate particle size distribution estimation system 11...Data input / output unit 12...Captured image preprocessing unit 13...Shape feature extraction unit 14...Color feature extraction unit 15...Machine learning model generation unit 16...Particle size distribution estimation unit 17...Feature importance evaluation unit 18...Image data storage unit 19...Feature storage unit 20...Machine learning model storage unit 21...Teacher data storage unit

Claims

1. This is an aggregate particle size distribution estimation system that estimates the particle size distribution of aggregate mixed in when producing concrete. a shape feature extraction unit that extracts shape feature quantities calculated from at least a contour length, a contour area, and a circularity of each of the aggregates as feature quantities of each of the captured aggregates from an aggregate surface image that is an image of the surface of the piled aggregates; a color feature extraction unit that extracts color feature values calculated from at least the gradation, hue, saturation, and brightness of color components of the aggregate as feature values of each captured aggregate from the aggregate surface image; a particle size distribution estimation unit that estimates the particle size distribution of the aggregate using a predetermined machine learning model by receiving the shape feature amount and the color feature amount; Equipped with The shape feature extraction unit the sum, average and standard deviation of the feature amounts of the contour length, the contour area and the circularity of each of the aggregates in the aggregate surface image are calculated as the shape feature amount; The color feature extraction unit classifies each feature amount of the gradient, hue, saturation, and brightness of each color component of the aggregate in the aggregate surface image into a plurality of ranges of feature size, and determines the occurrence rate of each range as the color feature amount.

2. The color components are a color component R, a color component G, and a color component B, and a gray scale calculated from each of the color components R, G, and B.

2. The aggregate particle size distribution estimation system according to claim 1.

3. a machine learning model generation unit that causes the machine learning model to learn using, as training data, each of the shape feature amount and the color feature amount extracted from the aggregate surface image obtained by capturing an image of the surface of a pile of aggregates having a known particle size distribution; The aggregate particle size distribution estimation system according to claim 1 or 2, further comprising:

4. The machine learning model generation unit The training data is divided into training data and verification data at a predetermined ratio, the machine learning model is trained using the training data, and the accuracy rate of the estimation results of the machine learning model is calculated using the verification data. This learning process is repeated a predetermined number of times, with the verification data being replaced with a portion of the training data.

4. The aggregate particle size distribution estimation system according to claim 3.

5. In the learning of the machine learning model, the contribution of each of the shape feature and the color feature to the learning result of the machine learning model is evaluated using a sorting importance technique. Feature Importance Evaluation Unit Further equipped 5. The aggregate particle size distribution estimation system according to claim 1, wherein the aggregate particle size distribution estimation system is a system for estimating particle size distribution of aggregates.

Images