Information processing device, information processing method, and program

Abstract

To reduce variations of accuracy of estimating a length and weight of an aquatic plant.SOLUTION: An information processing device 2 comprises: an acquisition unit 231 which acquires a photographed image obtained by imaging an aquatic plant living in the water from above, distance information indicating a distance from a position where the photographed image is captured to a water bottom and flow rate information indicating a flow rate of the water when the photographed image is captured; a first estimation unit 232 which estimates a length of the aquatic plant on the basis of a shape of the aquatic plant included in the photographed image, the distance information and the flow rate information; a second estimation unit 233 which estimates weight of the aquatic plant on the basis of the length of the aquatic plant estimated by the first estimation unit 232 and density of the aquatic plant included in the photographed image; and an output unit 234 which outputs the length of the aquatic plant estimated by the first estimation unit 232 and the weight of the aquatic plant estimated by the second estimation unit 233.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] In recent years, carbon absorbed in marine ecosystems, so-called blue carbon, has been attracting attention as a new option for a sink as a measure against global warming, and as a result, there is an increasing need to measure the length and weight of aquatic plants such as seaweed and marine algae that serve as a sink for CO2. Patent Document 1 discloses a technology for estimating the height and weight of a crop based on an image of the crop. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-157767 Summary of the Invention [Problem to be solved by the invention]

[0004] In the above technology, the object to be estimated for height and weight is a crop cultivated on land, but it seems that the height and weight of an aquatic plant can also be estimated based on an image of the aquatic plant. However, when the height and weight of an aquatic plant, i.e., the length and weight of the aquatic plant, are estimated using the above technology, there are cases where the accuracy of the estimation varies widely.

[0005] Therefore, the present invention has been made in consideration of these points, and aims to provide an information processing device, an information processing method, and a program that can reduce the variation in accuracy in estimating the length and weight of aquatic plants. [Means for solving the problem]

[0006] An information processing device according to a first aspect of the present invention has an acquisition unit that acquires an image of an aquatic plant living in water captured from above, distance information indicating the distance from the position where the image was captured to the bottom of the water, and flow velocity information indicating the flow velocity in the water at the time the image was captured, a first estimation unit that estimates the length of the aquatic plant based on the shape of the aquatic plant included in the image, the distance information, and the flow velocity information, a second estimation unit that estimates the weight of the aquatic plant based on the length of the aquatic plant estimated by the first estimation unit and the density of the aquatic plant included in the image, and an output unit that outputs the length of the aquatic plant estimated by the first estimation unit and the weight of the aquatic plant estimated by the second estimation unit.

[0007] The acquisition unit may acquire a plurality of captured images in which the aquatic plant is captured from above at different angles, and the first estimation unit may estimate the length of the aquatic plant based on the shape of the aquatic plant contained in each of the plurality of captured images.

[0008] The acquisition unit may acquire a first captured image, which is the captured image taken at a first position underwater, and a second captured image, which is the captured image taken at a second position shallower underwater than the first position, the first estimation unit may estimate a length of the aquatic plant based on a shape of the aquatic plant included in the first captured image, and the second estimation unit may estimate a weight of the aquatic plant based on a density of the aquatic plant included in the second captured image.

[0009] The information processing device may further have a generation unit that generates the machine learning model trained with training data including an image of an object whose length is to be estimated, the distance from the position where the image was captured to the bottom of the water, the underwater flow velocity at the time the image was captured, and the length of the object contained in the image, and that outputs the length of the object contained in the image by inputting the image, the distance, and the flow velocity, and the first estimation unit estimates the length of the aquatic plant by having the machine learning model output the length of the aquatic plant in response to inputting the captured image, the distance information, and the flow velocity information into the machine learning model.

[0010] The generation unit may generate the machine learning model for each type of the object, and the first estimation unit may estimate the length of the aquatic plant using one of the multiple machine learning models that corresponds to the type of the aquatic plant included in the captured image.

[0011] An information processing method according to a second aspect of the present invention includes the steps of: acquiring, executed by a computer, an image of an aquatic plant living in water captured from above, distance information indicating the distance from the position where the image was captured to the bottom of the water, and flow velocity information indicating the flow velocity in the water at the time the image was captured; estimating the length of the aquatic plant based on the shape of the aquatic plant included in the image, the distance information, and the flow velocity information; estimating the weight of the aquatic plant based on the estimated length of the aquatic plant and the density of the aquatic plant included in the image; and an output unit that outputs the estimated length and the estimated weight of the aquatic plant.

[0012] A program according to a third aspect of the present invention causes a computer to function as: an acquisition unit that acquires an image of an aquatic plant living in water captured from above, distance information indicating the distance from the position where the image was captured to the bottom of the water, and flow velocity information indicating the flow velocity in the water at the time the image was captured; a first estimation unit that estimates the length of the aquatic plant based on the shape of the aquatic plant included in the image, the distance information, and the flow velocity information; a second estimation unit that estimates the weight of the aquatic plant based on the length of the aquatic plant estimated by the first estimation unit and the density of the aquatic plant included in the image; and an output unit that outputs the length of the aquatic plant estimated by the first estimation unit and the weight of the aquatic plant estimated by the second estimation unit. Effect of the Invention

[0013] The present invention has the advantage of being able to reduce variation in accuracy in estimating the length and weight of an aquatic plant. [Brief description of the drawings]

[0014] [Figure 1] 1 is a diagram for explaining an overview of an information processing system S. [Diagram 2] FIG. 1 is a diagram showing a schematic representation of the shape of an aquatic plant. [Diagram 3] FIG. 2 is a diagram showing a configuration of an information processing device 2. [Figure 4] 13 is a flowchart showing a process flow of the information processing device 2. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] [Outline of Information Processing System S] FIG. 1 is a diagram for explaining an overview of an information processing system S. The information processing system S is a system used by a user to check the condition of an aquatic plant T in a habitat in which the aquatic plant T lives. The aquatic plant T is, for example, a plant that lives in water such as the sea and is attached to the bottom of the water. The aquatic plant T is, for example, seaweed or marine algae. The condition of the aquatic plant T includes, for example, the length of the aquatic plant T and the weight of the aquatic plant T. The information processing system S has a moving body 1 and an information processing device 2.

[0016] The moving body 1 is an unmanned vehicle that moves underwater, such as a drone. The moving body 1 is equipped with a collection unit C that collects information underwater. The collection unit C includes a camera that captures an image of the bottom of the water, a distance measurement sensor that measures the distance to the bottom of the water, and a current measurement sensor that measures the current speed in the water.

[0017] The degree of growth of the aquatic plants T inhabiting the habitat varies depending on the location of the habitat. For example, the closer to the center of the habitat, the higher the growth rate of the aquatic plants T, and the further from the center of the habitat, the lower the growth rate of the aquatic plants T. Therefore, it is necessary to check the condition of the aquatic plants T at various positions in the habitat. In this case, for the aquatic plants T at the edge of the habitat, the entire aquatic plant T can be captured by imaging it from the side, but for the aquatic plants T at the center of the habitat, it may be difficult to capture the entire aquatic plant T when imaging it from the side because other aquatic plants T are captured in the image.

[0018] When an aquatic plant T is imaged from above, the part of the aquatic plant T that is attached to the water bottom may not be captured, but if the distance from the water bottom to the imaging position where the image was captured is known, the length of the aquatic plant T can be estimated, and the condition of the aquatic plant T at various positions in its habitat can be confirmed. However, since there is a water current in the ocean and the aquatic plant T tilts depending on the speed of the water flow, the shape of the aquatic plant T when viewed from above changes depending on the tilt of the aquatic plant T.

[0019] FIG. 2 is a diagram showing a schematic representation of the shape of an aquatic plant T. FIG. 2(a) shows the state of an aquatic plant T1 when the flow speed is slow. As shown in FIG. 2(a), the aquatic plant T1 is only slightly affected by the water flow, and therefore has a small inclination. In this case, when the aquatic plant T1 is viewed from above, it takes the shape of an aquatic plant T1', and the visible area is small. FIG. 2(b) shows the state of an aquatic plant T2 when the flow speed is fast. As shown in FIG. 2(b), the aquatic plant T2 is more significantly affected by the water flow, and therefore has a large inclination. In this case, when the aquatic plant T2 is viewed from above, it takes the shape of an aquatic plant T2', and the observable area is large.

[0020] In this way, since the shape of the aquatic plant T when viewed from above changes depending on the flow speed, if the length and weight of the aquatic plant T are estimated based on an image taken from above and the distance from the water bottom to the imaging position, there will be a large difference between the length and weight of the aquatic plant T estimated based on the shape of the aquatic plant T1' and the length and weight of the aquatic plant T estimated based on the shape of the aquatic plant T2', and the accuracy of the estimation may vary greatly.

[0021] Therefore, the information processing system S estimates the length and weight of the aquatic plant T by taking into consideration the underwater flow speed at the time the captured image was captured. Hereinafter, the flow of the process executed by the information processing system S to estimate the length and weight of the aquatic plant T will be described with reference to FIG.

[0022] First, the moving body 1 collects information in its habitat and transmits the collected information to the information processing device 2 ((1) in FIG. 1). The collected information includes a captured image, distance information, and flow velocity information. The captured image is an image of the aquatic plant T captured from above. The captured image is a still image or a moving image. The distance information is information indicating the position at which the captured image was captured, i.e., the distance from the position of the distance measuring sensor to the bottom of the water. The flow velocity information is information indicating the underwater flow velocity at the time the captured image was captured.

[0023] When the information processing device 2 acquires the collected information, the information processing device 2 estimates the length of the aquatic plant T based on the captured image, distance information, and flow velocity information included in the collected information ((2) in FIG. 1). The information processing device 2 estimates the weight of the aquatic plant T based on the estimated length of the aquatic plant T and the captured image included in the collected information ((3) in FIG. 1).

[0024] Then, the information processing device 2 outputs estimation information including the estimated length and weight of the aquatic plant T ((4) in FIG. 1). In this way, the information processing system S can reduce the variation in accuracy in estimating the length and weight of the aquatic plant T. The configuration of the information processing device 2 will be described below.

[0025] [Configuration of information processing device 2] 3 is a diagram showing a configuration of the information processing device 2. The information processing device 2 has a communication unit 21, a storage unit 22, and a control unit 23. The control unit 23 has an acquisition unit 231, a first estimation unit 232, a second estimation unit 233, an output unit 234, and a generation unit 235.

[0026] The communication unit 21 is an interface for connecting to a network, and includes, for example, a communication controller. The storage unit 22 is a storage medium such as a ROM (Read Only Memory), a RAM (Random Access Memory), or a hard disk. The storage unit 22 stores a program executed by the control unit 23.

[0027] The control unit 23 is, for example, a CPU (Central Processing Unit). The control unit 23 executes a program stored in the storage unit 22 to function as an acquisition unit 231, a first estimation unit 232, a second estimation unit 233, an output unit 234, and a generation unit 235.

[0028] The acquisition unit 231 acquires collected information including a captured image, distance information, and flow velocity information. The acquisition unit 231 may acquire the collected information each time the collection unit C of the moving object 1 collects the collected information, or may acquire the collected information after the moving object 1 finishes collecting the collected information in the habitat of the aquatic plants.

[0029] The first estimation unit 232 estimates the length of the aquatic plant T based on the shape of the aquatic plant T included in the captured image, the distance information, and the flow speed information. For example, the first estimation unit 232 selects one aquatic plant from a plurality of aquatic plants T included in the captured image, and estimates the length of the aquatic plant T based on the shape of the selected aquatic plant T, the distance from the position of the distance measuring sensor to the bottom of the water when the captured image was captured, and the flow speed in the water when the captured image was captured. The first estimation unit 232 may estimate the length of each aquatic plant T included in the captured image, and estimate a statistical value (for example, an average value, a median value, a mode, etc.) of the estimated length of each aquatic plant T as the length of the aquatic plant T.

[0030] For example, the first estimation unit 232 estimates the length of the aquatic plant T included in each predetermined unit area in one or more captured images in which the entire habitat is captured. The predetermined unit area is, for example, a preset area.

[0031] For example, the storage unit 22 stores length reference data in which the shape of an object included in a reference image in which the object is captured from above, the distance from the position of the distance measuring sensor to the bottom of the water when the reference image is captured, the underwater flow velocity when the reference image is captured, and the length of the object included in the reference image are associated with each other. In this case, the first estimation unit 232 estimates the length of the aquatic plant T by referring to the length reference data.

[0032] Specifically, the first estimation unit 232 estimates the length of the aquatic plant T included in the captured image by identifying the length of an object that is relatively similar to the shape of the aquatic plant T included in the captured image (e.g., the object that is most similar to the shape of the aquatic plant T included in the captured image) among the shapes of multiple objects associated with the distance indicated by the distance information and the flow speed indicated by the flow speed information in the length reference data. The object that is relatively similar to the shape of the aquatic plant T is, for example, an object whose area, length, and width are relatively similar to those of the aquatic plant T included in the captured image.

[0033] The first estimation unit 232 may estimate the length of the aquatic plant T using a plurality of captured images. For example, the collection unit C of the moving body 1 includes a plurality of cameras that capture images of the water bottom at different angles. In this case, first, the acquisition unit 231 acquires a plurality of captured images of the aquatic plant T captured from different angles above. Then, the first estimation unit 232 estimates the length of the aquatic plant T based on the shape of the aquatic plant T included in each of the plurality of captured images. For example, the first estimation unit 232 generates a three-dimensional model of the aquatic plant T based on the plurality of captured images, and estimates the length of the aquatic plant T based on the shape of the generated three-dimensional model. In this way, the information processing device 2 can improve the accuracy of estimating the length of the aquatic plant T.

[0034] The first estimation unit 232 may estimate the length of the aquatic plant T using a machine learning model. The machine learning model is a model that outputs the length of an object included in an image by inputting an image, a distance, and a flow speed. The machine learning model is, for example, a machine learning model of a convolutional neural network.

[0035] The machine learning model, for example, converts multiple input images into a single-dimensional feature vector, and infers the length of an object contained in the image using a regression model based on the converted feature vector, the input distance, and the input flow velocity. By using multiple images, the machine learning model can obtain the feature amount of the object contained in each image and estimate the length of the object even when the water is murky. The machine learning model may estimate the length of the object using one image.

[0036] Specifically, the generating unit 235 first generates a machine learning model trained with training data. The training data is data including an image of an object whose length is to be estimated, a distance from the position where the image was captured to the bottom of the water, the underwater flow speed when the image was captured, and the length of the object included in the image. Then, the first estimating unit 232 estimates the length of the aquatic plant T by having the machine learning model output the length of the aquatic plant T in response to inputting the captured image, distance information, and flow speed information to the machine learning model.

[0037] For example, first, the generation unit 235 generates a machine learning model and trains the machine learning model using teacher data. The generation unit 235 stores the trained machine learning model in the storage unit 22. Then, the first estimation unit 232 acquires the machine learning model stored in the storage unit 22, and causes the machine learning model to output the length of the aquatic plant T in response to inputting the captured image, distance information, and flow velocity information to the machine learning model. In this way, the information processing device 2 can improve the accuracy of estimating the length of the aquatic plant T.

[0038] The length of the aquatic plant T varies depending on the type of the aquatic plant T. Therefore, the first estimation unit 232 may estimate the length of the aquatic plant T using a machine learning model corresponding to the type of the aquatic plant T. Specifically, first, the generation unit 235 generates a machine learning model for each type of object. Then, the first estimation unit 232 estimates the length of the aquatic plant T using, of the multiple machine learning models, a machine learning model corresponding to the type of the aquatic plant T included in the captured image.

[0039] For example, the type of the aquatic plant T is set in advance by a user who uses the information processing device 2, and the first estimation unit 232 estimates the length of the aquatic plant T using a machine learning model corresponding to the set type of the aquatic plant T. The first estimation unit 232 may identify the type of the aquatic plant T included in the captured image by analyzing the captured image, and estimate the length of the aquatic plant T using the machine learning model corresponding to the identified type of the aquatic plant T. In this way, the information processing device 2 can improve the accuracy of estimating the length of the aquatic plant T.

[0040] The second estimation unit 233 estimates the weight of the aquatic plants T based on the length of the aquatic plants T estimated by the first estimation unit 232 and the density of the aquatic plants T included in the captured image. For example, the second estimation unit 233 estimates the weight of the aquatic plants T present in a unit area for each predetermined unit area based on the length of the aquatic plants corresponding to the unit area and the density of the aquatic plants T in the unit area, and calculates the total weight of the aquatic plants T in the habitat by summing up the estimated weights of the aquatic plants T.

[0041] For example, the storage unit 22 stores density reference data in which the areas of objects included in a reference image in which multiple objects are captured from above are associated with the densities of the objects. In this case, first, the second estimation unit 233 calculates the area of ​​the aquatic plant T included in the captured image. The second estimation unit 233 refers to the density reference data and identifies, among the areas of the multiple objects, the density of an object that is relatively close to the calculated area of ​​the aquatic plant T (e.g., an object that is closest to the calculated area of ​​the aquatic plant T) as the density of the aquatic plant T. Then, the second estimation unit 233 estimates the weight of the aquatic plant T by multiplying the length of the aquatic plant T identified by the first estimation unit 232 by the identified density of the aquatic plant T.

[0042] The second estimation unit 233 may estimate the weight of the aquatic plant T based on the length of the aquatic plant T estimated by the first estimation unit 232 and the density of the aquatic plant T based on the distance information and the flow speed information. For example, the density reference data stored in the storage unit 22 is further associated with the distance from the position of the distance measuring sensor to the bottom of the water when the reference image was captured, and the flow speed in the water when the reference image was captured. In this case, the second estimation unit 233 refers to the density reference data and estimates the weight of the aquatic plant T using the density of the object corresponding to the area of ​​the aquatic plant T included in the captured image, the distance indicated by the distance information, and the flow speed indicated by the flow speed information.

[0043] In the above, an example has been described in which the information processing device 2 estimates the length and weight of the aquatic plant T using the same captured image, but this is not limiting. For example, the closer the distance between the captured image and the aquatic plant T, the higher the accuracy of the estimation of the length of the aquatic plant T. Also, the wider the imaging range of the captured image, the more weight of the aquatic plant T can be estimated. Thus, the information processing device 2 may estimate the length and weight of the aquatic plant T using multiple captured images each having a different distance from the imaging position to the water bottom.

[0044] For example, the moving body 1 collects first collected information collected at a first position where the collecting unit C operates downward and second collected information collected at a second position where the collecting unit C operates above the first position. In this case, the acquiring unit 231 first acquires a first captured image and a second captured image captured at a second position shallower in water than the first position. The first captured image is a captured image captured at the first position underwater and is included in the first collected information. The second captured image is a captured image captured at a second position shallower in water than the first position and is included in the second collected information.

[0045] The first estimation unit 232 estimates the length of the aquatic plant T based on the shape of the aquatic plant T included in the first captured image. Then, the second estimation unit 233 estimates the weight of the aquatic plant T based on the density of the aquatic plant T included in the second captured image. In this way, the information processing device 2 can estimate the weight of aquatic plants T over a wide range while improving the accuracy of estimating the length of the aquatic plant T.

[0046] The output unit 234 outputs estimation information including the length of the aquatic plant T estimated by the first estimation unit 232 and the weight of the aquatic plant T estimated by the second estimation unit 233. The output unit 234 displays the estimation information on, for example, a display (not shown) included in the information processing device 2. The output unit 234 may transmit the estimation information via the communication unit 21 to a terminal (not shown) used by a user.

[0047] The output unit 234 may output estimation information including the length of the aquatic plant T estimated for each predetermined unit area and the weight of the aquatic plant T estimated for each unit area. The output unit 234 may also output estimation information including a statistical value (e.g., average value, median value, mode, etc.) of the length of the aquatic plant T estimated for each predetermined unit area and the total weight of the aquatic plant T in the habitat.

[0048] [Processing of information processing device 2] Next, a description will be given of the process flow of the information processing device 2. Fig. 4 is a flowchart showing the process flow of the information processing device 2. This flowchart starts when the acquisition unit 231 acquires collected information including a captured image, distance information, and flow velocity information from the moving object 1 (S1).

[0049] The first estimation unit 232 sets an estimation range for estimating the length and weight of the aquatic plant T based on one or more captured images in which the entire habitat is captured (S2). The estimation range is a range indicating a predetermined unit area, and is a range in which the length and weight of the aquatic plant T have not yet been estimated.

[0050] The first estimation unit 232 estimates the length of the aquatic plant T present in the estimation range based on the shape of the aquatic plant T included in the captured image, the distance information, and the flow speed information (S3). The second estimation unit 233 estimates the weight of the aquatic plant T present in the estimation range based on the length of the aquatic plant T estimated by the first estimation unit 232 and the density of the aquatic plant T present in the estimation range included in the captured image (S4).

[0051] The second estimation unit 233 determines whether there are other estimation ranges, that is, whether there are other estimation ranges for which the length and weight of the aquatic plant T have not yet been estimated (S5). When the second estimation unit 233 determines that there are other estimation ranges (YES in S5), the process returns to S2.

[0052] On the other hand, if the second estimation unit 233 determines that there is no other estimation range (NO in S5), it calculates the total weight of the aquatic plants T in the habitat by adding up the estimated weights of each aquatic plant T (S6). Then, the output unit 234 outputs the estimation information (S7).

[0053] [Effects of this embodiment] As described above, the information processing device 2 estimates the length of the aquatic plant T based on the shape of the aquatic plant T included in the captured image, distance information, and flow velocity information, and estimates the weight of the aquatic plant T based on the estimated length of the aquatic plant T and the density of the aquatic plant T included in the captured image. Then, the information processing device 2 outputs the estimated length and weight of the aquatic plant T. In this way, the information processing device 2 can reduce the variation in accuracy of estimating the length and weight of the aquatic plant T.

[0054] Furthermore, this invention will make it possible to contribute to Goal 9 of the United Nations' Sustainable Development Goals (SDGs), which is to "build resilient infrastructure, promote industry, innovation and infrastructure."

[0055] Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of the gist of the present invention. For example, all or part of the device can be configured by distributing or integrating functionally or physically in any unit. In addition, new embodiments resulting from any combination of multiple embodiments are also included in the embodiments of the present invention. The effect of the new embodiment resulting from the combination combines the effect of the original embodiment. [Explanation of symbols]

[0056] 1. Mobile 2. Information processing equipment 21 Communications Department 22 Memory section 23 Control Unit 231 Acquisition Department 232 1st estimation part 233 Second estimation part 234 Output section 235 Generation part C Collection Department S Information Processing System

Claims

1. an acquisition unit that acquires an image captured from underwater of an aquatic plant living in the water as a subject, the image being captured from above the aquatic plant, distance information indicating the distance from a position where the image was captured to the water bottom, and flow velocity information indicating the flow velocity in the water at the time the image was captured; a first estimation unit that estimates a length of the aquatic plant based on a shape of the aquatic plant included in the captured image, the distance information, and the flow velocity information; a second estimation unit that estimates a weight of the aquatic plant based on the length of the aquatic plant estimated by the first estimation unit and a density of the aquatic plant included in the captured image; an output unit that outputs the length of the aquatic plant estimated by the first estimation unit and the weight of the aquatic plant estimated by the second estimation unit; An information processing device having the above configuration.

2. The acquisition unit acquires a plurality of captured images of the aquatic plant captured from different angles above the aquatic plant, The first estimation unit estimates a length of the aquatic plant based on a shape of the aquatic plant included in each of the plurality of captured images. The information processing device according to claim 1 .

3. The acquisition unit acquires a first captured image, which is the captured image captured at a first position underwater, and a second captured image, which is the captured image captured at a second position underwater that is shallower than the first position; The first estimation unit estimates a length of the aquatic plant based on a shape of the aquatic plant included in the first captured image, The second estimation unit estimates a weight of the aquatic plant based on a density of the aquatic plant included in the second captured image.

3. The information processing device according to claim 1 or 2.

4. a machine learning model trained with training data including an image of an object whose length is to be estimated, a distance from the position where the image was captured to the bottom of the water, an underwater current speed at the time the image was captured, and a length of the object included in the image, the machine learning model further comprising a generation unit that generates the machine learning model by inputting the image, the distance, and the current speed, and outputs the length of the object included in the image; the first estimation unit estimates the length of the aquatic plant by causing the machine learning model to output the length of the aquatic plant in response to inputting the captured image, the distance information, and the flow velocity information to the machine learning model; The information processing device according to claim 1 .

5. The generation unit generates the machine learning model for each type of the object, the first estimation unit estimates a length of the aquatic plant by using a machine learning model corresponding to a type of the aquatic plant included in the captured image, among the plurality of machine learning models; The information processing device according to claim 4.

6. The computer executes acquiring an image of an aquatic plant living in water as a subject, the image being captured from underwater, the image being captured from above the aquatic plant, distance information indicating the distance from the position where the image was captured to the bottom of the water, and flow velocity information indicating the flow velocity in the water at the time the image was captured; estimating a length of the aquatic plant based on a shape of the aquatic plant included in the captured image, the distance information, and the flow velocity information; estimating a weight of the aquatic plant based on the estimated length of the aquatic plant and a density of the aquatic plant included in the captured image; an output unit that outputs the estimated length and the estimated weight of the aquatic plant; An information processing method comprising the steps of:

7. Computer, an acquisition unit that acquires an image captured from underwater of an aquatic plant living in the water as a subject, the image being captured from above the aquatic plant, distance information indicating a distance from a position where the image was captured to a water bottom, and flow velocity information indicating a flow velocity in the water at the time the image was captured; a first estimation unit that estimates a length of the aquatic plant based on a shape of the aquatic plant included in the captured image, the distance information, and the flow velocity information; a second estimation unit that estimates a weight of the aquatic plant based on the length of the aquatic plant estimated by the first estimation unit and a density of the aquatic plant included in the captured image; and an output unit that outputs the length of the aquatic plant estimated by the first estimation unit and the weight of the aquatic plant estimated by the second estimation unit; A program to function as a

Images