Classifications

• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
  • G06N20/00—Machine learning
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
  • G06T19/00—Manipulating three-dimensional [3D] models or images for computer graphics

Definitions

• This disclosure relates to a biological model generation device, a biological model generation program, and a biological model generation method.
• products are sometimes evaluated through simulations using human body models.
• image data created using a 3D human body model may be used instead of 2D image data of occupants in the vehicle, and the accuracy of occupant detection may be evaluated through simulation.
• Patent Document 1 A system for evaluating products through simulations using human body models has been disclosed (see Patent Document 1).
• Patent Document 1 describes how human body shape data obtained by three-dimensionally measuring each part of the human body is appropriately modified to generate several types of human body models, such as a standard body model, and large or small body models, allowing users to evaluate a wide range of products.
• the present disclosure aims to solve the above-mentioned problems by providing a biological model generation device, a biological model generation program, and a biological model generation method that can generate a three-dimensional model of a living organism with a natural external shape.
• the biological model generation device is characterized by comprising: a parameter acquisition unit that acquires the value of a first parameter related to the external shape of a specific living organism; an estimation unit that calculates an estimated value of a second parameter that indicates the external shape of the living organism corresponding to the value of the first parameter based on statistical data related to the external shapes of multiple living organisms of the same type as the specific living organism and the value of the first parameter acquired by the parameter acquisition unit; and a biological model generation unit that generates a three-dimensional model of the living organism corresponding to the value of the first parameter and the estimated value of the second parameter based on the value of the first parameter acquired by the parameter acquisition unit and the estimated value of the second parameter calculated by the estimation unit.
• estimated values of other parameters that indicate the external shape of a living organism are calculated based on statistical data regarding the external shape of the organism and the values of the organism's parameters, and a three-dimensional model of the organism is generated based on the calculated estimated parameter values, making it possible to generate a three-dimensional model of the organism with a natural external shape.
• FIG. 1 is a block diagram showing a schematic configuration of a biological model generating device according to a first embodiment.
• FIG. 2 is a block diagram showing the configuration of a parameter estimation unit according to the first embodiment.
• FIG. 1 is a block diagram showing an example of the hardware configuration of a biological model generating device according to a first embodiment.
• FIG. 1 is a block diagram showing an example of the hardware configuration of a biological model generating device according to a first embodiment.
• 4 is a flowchart showing processing performed by the biological model generating device according to the first embodiment.
• 10 is a table showing an example of statistical data acquired by the biological model generating device according to the first embodiment.
• FIG. 10 is a block diagram showing the configuration of a parameter estimation unit according to a second embodiment.
• FIG. 11 is a block diagram showing the configuration of a parameter estimation unit according to a third embodiment.
• FIG. 11 is a block diagram showing the configuration of a parameter estimation unit according to a fourth embodiment.
• FIG. 13 is a block diagram showing the configuration of a parameter estimation unit according to a fifth embodiment.
• FIG. 1 is a block diagram showing a schematic configuration of the biological model generating device according to embodiment 1.
• the biological model generating device 100 according to embodiment 1 is a device that estimates values of other parameters that indicate the external shape of a living organism based on the values of specific parameters input by a user, and generates a three-dimensional model of the living organism based on these parameter values.
• the biological model generating device 100 also generates two-dimensional image data based on the generated three-dimensional model of the living organism.
• the living organism for which the biological model generating device 100 generates a three-dimensional model may be a human body, a living organism of a specific type of animal other than a human body, or any other living organism.
• the biological model generation device 100 comprises an input unit 10, a parameter estimation unit 20, a biological model generation unit 30, a virtual environment generation unit 40, and an output unit 50.
• the biological model generation device 100 is also electrically connected to an input device (not shown) and an external device (not shown) via wired or wireless connections so that they can communicate with each other.
• the input device inputs information to the biological model generation device 100.
• the input device is a keyboard, mouse, or other device that accepts user input operations, and inputs information corresponding to the user input operations to the biological model generation device 100.
• the input device is another computer, server, database, or other device connected to the biological model generation device 100, and inputs information to the biological model generation device 100 based on a predetermined trigger.
• the external device accepts information output from the biological model generating device 100.
• the external device may be configured as a display device such as a liquid crystal panel that displays information output from the biological model generating device 100.
• the external device may be configured as a computer, server, database, or other device that performs specific processing based on the information output from the biological model generating device 100.
• the input device and external device may be configured integrally with the biological model generating device 100, or may each be configured as multiple devices electrically connected to each other, or the biological model generating device 100 may be configured as multiple devices electrically connected to each other.
• the input unit 10 accepts information from an input device.
• the input unit 10 accepts information from the input device indicating the values of one or more parameters related to the external shape of the living organism, which are used when generating a three-dimensional model of the living organism.
• the input unit 10 acquires information indicating the values of one or more parameters related to the external shape of the living organism, which are used when generating a three-dimensional model of the living organism.
• the parameters related to the external shape of the living organism that the input unit 10 acquires from the input device are also referred to as first parameters.
• the first parameters are parameters related to the overall external shape of the living organism or the external shapes of major parts of the living organism, and are major parameters for determining the external shape of the living organism.
• the input unit 10 receives from the input device, as information indicating the value of the first parameter, information indicating the value of a parameter related to the body length of the living organism and information indicating the value of a parameter related to the body shape of the living organism. Specifically, the input unit 10 receives from the input device information indicating the height of the living organism as a parameter related to the body length of the living organism, and information indicating the weight of the living organism as a parameter related to the body shape of the living organism.
• the body shape of a living organism refers to categories such as thin, obese, and normal, or the ratio of the length of a specific part of the living organism to the length of other parts. Generally, in living organisms of the same species, there is a correlation between weight and body shape.
• the weight of a living organism can be said to be a parameter related to the body shape of the living organism.
• a parameter related to the body shape of a living organism other than weight can be the circumference of a specific part of the living organism, such as chest circumference or abdominal circumference.
• the heavier the weight, the larger the external shape of the living organism, and the lighter the weight the smaller the external shape of the living organism. Therefore, the weight of a living organism can be said to be a parameter related to the external shape of the living organism.
• the input unit 10 receives from the input device, as information indicating the value of the first parameter, information indicating the value of a parameter relating to the size of the external shape of the living body along a first direction, and information indicating the value of a parameter relating to the size of the external shape of the living body along a second direction intersecting the first direction.
• the input unit 10 receives from the input device information indicating the size of the living body in the longitudinal direction as a parameter relating to the size of the external shape of the living body along the first direction, and information indicating the size in the width direction, which is a direction perpendicular to the longitudinal direction of the living body, as a parameter relating to the size of the external shape of the living body along the second direction.
• the information indicating the size in the width direction of the living body may be the length of the living body in the width direction, or the perimeter of the living body along the direction perpendicular to the longitudinal direction of the living body.
• the first parameter is not limited to parameters that can be directly expressed numerically, such as the size of a specific body part.
• the first parameter may also be a parameter that is normally expressed as a non-numeric value, such as gender or race. For example, by assigning a numerical value to each gender or race in advance, the gender or race as the first parameter can be treated as a numerical value.
• other first parameters include age, generation, etc.
• the input unit 10 receives from the input device information for deforming the three-dimensional model of the living organism and information regarding the conditions for generating planar image data based on the three-dimensional model of the living organism.
• the input unit 10 receives from the input device information for changing the position and orientation of the three-dimensional model of the living organism in a specific coordinate system as information for deforming the three-dimensional model of the living organism.
• the input unit 10 receives from the input device information for changing the posture, such as the angles of the joints of the three-dimensional model of the living organism, as information for deforming the three-dimensional model of the living organism.
• the input unit 10 receives from the input device information for changing the facial expression of the three-dimensional model of the living organism as information for deforming the three-dimensional model of the living organism.
• the input unit 10 receives from the input device information for processing the three-dimensional model of a living organism, such as information for changing the appearance of the surface of the three-dimensional model, such as the color, pattern, fine irregularities, and light reflectance of the three-dimensional model of a living organism.
• the input unit 10 receives from the input device, as information regarding the conditions for generating planar image data based on a three-dimensional model of a living organism, information indicating the position of the viewpoint when generating planar image data of the three-dimensional model viewed from a specific viewpoint; information indicating the position, brightness, color of the light source, ambient scattered light, and other light irradiation conditions when generating planar image data in a state where light is irradiated from a specific light source onto the three-dimensional model; information regarding the background of the three-dimensional model when generating planar image data based on the three-dimensional model of a living organism; and information regarding other objects to be included in the planar image data together with the three-dimensional model when generating planar image data based on the three-dimensional model of a living organism.
• the input device only needs to be configured to input information indicating the value of at least one parameter related to the external shape of the living organism into the input unit 10.
• the input device may be configured to input all of the above-mentioned information into the input unit 10, or may be configured to input any one or more of the above-mentioned information into the input unit 10.
• the parameter estimation unit 20 estimates the value of a parameter other than the first parameter that indicates the external shape of the living body.
• the parameter related to the external shape of the living body estimated by the parameter estimation unit 20 is also referred to as the second parameter.
• the second parameter is a parameter related to the external shape of an individual part of the living body, and is a detailed parameter used to determine the external shape of the living body by comparing it with the first parameter.
• Figure 2 is a block diagram showing the configuration of the parameter estimation unit 20 according to embodiment 1. As shown in Figure 2, the parameter estimation unit 20 according to embodiment 1 includes a parameter acquisition unit 21, an estimation unit 22, and a memory unit 25.
• the parameter acquisition unit 21 acquires the value of a first parameter of the living body via the input unit 10 in order to estimate the value of a second parameter of the living body.
• the memory unit 25 stores various information for estimating the value of the second parameter of the living body.
• the estimation unit 22 calculates an estimated value of the second parameter of the living body based on the value of one or more first parameters acquired by the parameter acquisition unit 21 and the information stored in the memory unit 25. For example, the estimation unit 22 calculates, as the value of the second parameter of the living body, estimated values of the dimensions of one or more parts of the living body, such as the size of the living body's head, shoulder width, chest circumference, arm length, arm thickness, leg length, leg thickness, etc. Furthermore, for example, the estimation unit 22 calculates, as the value of the second parameter of the living body, estimated values of coordinates indicating the position of a specific part of the living body in a specific coordinate system.
• the estimation unit 22 calculates an estimated value of a second parameter of a living body based on statistical data relating to the external shapes of multiple living bodies and the value of the first parameter acquired by the parameter acquisition unit 21. Specifically, the estimation unit 22 calculates an estimated value of the second parameter of a living body based on statistical data of the second parameter for the first parameter of the living body, calculated based on actual measured values of the first parameter and second parameter of multiple living bodies stored in advance in the storage unit 25, and the value of the first parameter acquired by the parameter acquisition unit 21.
• the estimation unit 22 calculates an estimated value of the second parameter of the living body based on a trained model generated based on statistical data of actual measurement values of first parameter values and second parameter values of a plurality of living bodies, which is stored in advance in the storage unit 25, and the value of the first parameter acquired by the parameter acquisition unit 21. Specifically, the estimation unit 22 calculates an estimated value of the second parameter of the living body using a trained model that is stored in advance in the storage unit 25 and that is generated by machine learning such as deep learning using a data set of the value of the first parameter of the living body and statistical data of the value of the second parameter corresponding to the value of the first parameter, and that calculates the value of the second parameter corresponding to the first parameter by inputting the value of a specific first parameter.
• the estimation unit 22 is a trained model stored in advance in the memory unit 25, and is generated by machine learning such as deep learning using statistical data obtained by surveying multiple human bodies as a data set, which includes a combination of data having height and weight values, which are first parameters of a specific human body, and shoulder width values, which are second parameters corresponding to the values of the first parameters of the specific human body.By inputting specific height and weight values, the trained model calculates an estimated value of shoulder width using the trained model to calculate the shoulder width value corresponding to the height and weight.
• the estimation unit 22 which calculates an estimated value of the second parameter of the living organism using such a trained model and the value of the first parameter acquired by the parameter acquisition unit 21, can be said to calculate an estimated value of the second parameter of the living organism based on statistical data on the external shapes of multiple living organisms and the value of the first parameter acquired by the parameter acquisition unit 21.
• such statistical data may include a representative value of the value of a second parameter corresponding to the value of a first parameter of a living organism, a variability index, a probability density function, etc.
• the estimation unit 22 can calculate, as an estimated value, a representative value of the second parameter of a living organism based on the value of the first parameter of the living organism.
• the estimation unit 22 can calculate, as estimated values, a plurality of second parameters according to the distribution of variability of the second parameter of a living organism corresponding to the value of the first parameter, based on the value of the first parameter of the living organism.
• the model used for machine learning may be a general linear regression model or a neural network.
• the model used for machine learning may also be Gaussian process regression, which makes it possible to output statistical data for a second parameter based on the value of a specific first parameter.
• Gaussian process regression as the model used for machine learning, it becomes possible to input a combination of height and weight as the first parameter and calculate statistical data for shoulder width, such as the mean and variance of shoulder width, by learning to output the shoulder width corresponding to the input height and weight.
• shoulder width such as the mean and variance of shoulder width
• using such a model makes it possible to calculate the actual range of the second parameter corresponding to the specific first parameter.
• estimation unit 22 is configured to calculate an estimated value of the second parameter of the living body based on the values of two or more first parameters acquired by the parameter acquisition unit 21.
• the estimation unit 22 outputs the calculation results of the estimated value to the biological model generation unit 30.
• the biological model generation unit 30 shown in FIG. 1 generates a three-dimensional model of a living organism corresponding to the value of the first parameter and the estimated value of the second parameter, based on the value of the first parameter acquired by the input unit 10 and the estimated value of the second parameter calculated by the estimation unit 22.
• the biological model generation unit 30 generates a three-dimensional model of a living organism, which is information indicating a three-dimensional shape expressed using polygon data, volume data, point cloud data, etc.
• the biological model generation unit 30 may be configured to acquire the value of the first parameter via the parameter estimation unit 20.
• the biological model generation unit 30 references information about a three-dimensional model of a standard living organism that serves as a base body, which is stored in advance in the storage unit 25, and adjusts the length and thickness of each part of the three-dimensional model according to the value of the first parameter and the estimated value of the second parameter, thereby generating a three-dimensional model of the living organism that corresponds to the value of the first parameter and the estimated value of the second parameter.
• the biological model generation unit 30 outputs biological model information indicating the generated three-dimensional model of the living organism to the virtual environment generation unit 40.
• the storage unit 25 may store multiple three-dimensional models corresponding to gender, race, and age as three-dimensional models of a standard living organism to be used as a base body, and the biological model generation unit 30 may be configured to select one of these multiple three-dimensional models based on the value of the first parameter acquired by the input unit 10, and generate a three-dimensional model of the organism based on the selected three-dimensional model according to the value of the first parameter and the estimated value of the second parameter.
• the biological model generation unit 30 may be configured to select two or more three-dimensional models from the three or more three-dimensional models stored in the storage unit 25 based on either or both of the value of the first parameter and the estimated value of the second parameter, and synthesize these three-dimensional models after weighting each of the two or more selected three-dimensional models according to either or both of the value of the first parameter and the estimated value of the second parameter.
• the virtual environment generation unit 40 which serves as a three-dimensional model conversion unit, performs transformations, such as converting and adding information, on the three-dimensional model of the living organism generated by the biological model generation unit 30, and then generates two-dimensional image data including the three-dimensional model.
• the virtual environment generation unit 40 transforms the three-dimensional model of the living organism generated by the biological model generation unit 30 into another three-dimensional model based on information for transforming the three-dimensional model acquired by the input unit 10.
• the virtual environment generation unit 40 changes the posture of the three-dimensional model of the living organism generated by the biological model generation unit 30 based on information for changing the posture of the three-dimensional model.
• the virtual environment generation unit 40 transforms the three-dimensional model of the living organism generated by the biological model generation unit 30 so that the posture of the three-dimensional model of the living organism generated by the biological model generation unit 30 becomes a different posture, based on information for changing the posture of the three-dimensional model.
• posture can include whether the living organism is standing or sitting, the direction of the face relative to the orientation of the torso, whether the arms are crossed, etc.
• the virtual environment generation unit 40 changes the position and orientation in a specific coordinate system of the three-dimensional model of the living organism generated by the biological model generation unit 30 based on information for changing the position and orientation of the three-dimensional model in a specific coordinate system.
• the virtual environment generation unit 40 converts the three-dimensional model of the living organism generated by the biological model generation unit 30 into planar image data viewed from a specific viewpoint. At this time, the virtual environment generation unit 40 converts the three-dimensional model of the living organism generated by the biological model generation unit 30 into planar image data in a specific file format that virtually shows the state in which the living organism represented by the three-dimensional model is located in a specific environment.
• the virtual environment generation unit 40 converts the three-dimensional model of the living organism generated by the biological model generation unit 30 into planar image data by including information about the background of the living organism and objects present around the living organism in the image based on the values of parameters indicating the environment surrounding the living organism acquired by the input unit 10, so that the converted planar image data becomes planar image data that virtually shows the state in which the living organism is located in a specific environment, such as a room, a car cabin, a gymnasium, or an urban landscape.
• a specific environment such as a room, a car cabin, a gymnasium, or an urban landscape.
• the virtual environment generation unit 40 converts the three-dimensional model of the living organism generated by the living organism model generation unit 30 into planar image data, based on information acquired by the input unit 10 indicating the light irradiation conditions when the three-dimensional model is irradiated with light, so that the converted planar image data becomes planar image data that virtually indicates the state in which the living organism is being irradiated with light.
• the specific environment in which the living organism is located is not limited to one that imitates a realistic environment.
• the specific environment in which the living organism is located may be one that matches the intended use of the planar image data, and may have a solid black background, for example.
• the virtual environment generation unit 40 outputs virtual environment information, which is information indicating the planar image data into which the three-dimensional model has been converted, to the output unit.
• the output unit 50 outputs the virtual environment information from the virtual environment generation unit 40 to an external device.
• the external device virtually evaluates the operational performance of a device that performs image recognition using image data through a simulation, based on the virtual environment information acquired from the output unit 50.
• the external device generates learning data for a learning device that performs image recognition using image data, based on the virtual environment information acquired from the output unit 50.
• Figure 3 is a block diagram showing an example of the hardware configuration of the biological model generating device 100 according to embodiment 1
• Figure 4 is a block diagram showing an example of a hardware configuration of the biological model generating device 100 according to embodiment 1 that is different from that shown in Figure 2.
• the biological model generating device 100 has a processor 100a, a memory 100b, and an I/O port 100c, and is configured so that the processor 100a reads and executes programs stored in the memory 100b.
• the memory 100b is composed of, for example, non-volatile or volatile semiconductor memory such as RAM, ROM, flash memory, EPROM, EEPROM, etc., or a combination of these.
• the memory 100b may also be a magnetic disk, flexible disk, optical disk, compact disk, minidisk, DVD, etc.
• the memory 100b may also be an HDD or SSD.
• the biological model generating device 100 has a processing circuit 100d and an I/O port 100c, which are dedicated hardware.
• the processing circuit 100d is configured, for example, by a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, a system LSI (Large-Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination of these.
• Each function of the biological model generating device 100 is realized by the processor 100a or the processing circuit 100d, which is dedicated hardware, executing a program, which is software, firmware, or a combination of software and firmware.
• the biological model generating device 100 may also have hardware other than the above.
• FIG. 5 is a flowchart showing the processing performed by the biological model generation device 100 according to embodiment 1.
• the biological model generation device 100 starts processing, it first acquires, from the input device, the value of a first parameter of a specific human body, i.e., the human body for which a three-dimensional model is to be generated (step ST1).
• the biological model generation device 100 acquires, from the input device via the input unit 10, information indicating height as the value of the first first parameter and weight as the value of the second first parameter.
• the biological model generating device 100 calculates an estimated value of the second parameter based on the value of the first parameter (step ST2). In this processing, the biological model generating device 100 calculates an estimated value of the second parameter indicating the external shape of the human body corresponding to the value of the first parameter based on statistical data regarding the external shapes of multiple human bodies and the value of the first parameter of a specific human body acquired in the processing of step ST1.
• FIG. 6 is a table showing an example of statistical data acquired by the biological model generating device 100 according to embodiment 1.
• FIG. 6 is a table showing the average value, which is a representative value of shoulder width, and the standard deviation, which is an index of shoulder width variation, as statistical data on shoulder width corresponding to height and weight, which are first parameters.
• the table in FIG. 6 indicates that the average value of shoulder width for a human body with a height of 150-160 cm and a weight of 50-60 kg is 35 cm, and the standard deviation of shoulder width for this human body is 5 cm.
• step ST2 if the height and weight of a specific human body acquired in the processing of step ST1 are 155 cm and 55 kg, respectively, the biological model generating device 100 calculates an estimated value of shoulder width for this human body to be 35 cm based on the table in FIG. 6.
• the estimation unit 22 can calculate an estimated value of shoulder width based on statistical data obtained based on the actual measurement values of a person who falls within the range of 150 to 160 cm and 50 to 60 kg.
• the biological model generating device 100 may be configured to calculate, depending on the application of the three-dimensional human body model, a value that is different from a representative value calculated based on statistical data on shoulder width as an estimated value of shoulder width corresponding to the height and weight of the specific human body obtained in the processing of step ST1.
• the biological model generating device 100 may be configured to calculate one or both of the substantial upper and lower limits of shoulder width that take variability into account as an estimated value of shoulder width corresponding to the height and weight of the specific human body obtained in the processing of step ST1.
• the biological model generation device 100 may be configured to calculate a value obtained by subtracting twice the standard deviation from the average value as the lower limit of the shoulder width corresponding to the height and weight of the specific human body obtained in the processing of step ST1, and to calculate a value obtained by adding twice the standard deviation to the average value as the upper limit of the shoulder width corresponding to the height and weight of the specific human body obtained in the processing of step ST1. For example, by calculating the actual upper and lower limits of the second parameter in this manner, it becomes possible to determine the boundary values of the range in which the device can recognize images by simulating the evaluation of the operating performance of a device that performs image recognition using image data using virtual environment information generated based on the upper and lower limits.
• the above formula is an example of a formula for calculating the actual upper or lower limit, and it is possible to set a formula for calculating the upper or lower limit of a range that is considered statistically valid depending on the application of the three-dimensional human body model to be generated.
• the statistical data used to calculate the estimated value of the second parameter is required to be statistical data about a living organism of the same species as the living organism for which the model is being generated. For example, when calculating the estimated value of the second parameter of the human body, statistical data about animals other than humans cannot be used. Furthermore, by using statistical data about the same attributes of the living organism as the one being estimated, such as age, gender, and race, more accurate estimation of the second parameter is possible.
• the biological model generating device 100 may be configured to calculate multiple estimated values as shoulder width estimates corresponding to the height and weight of a specific human body obtained in the processing of step ST1, depending on the use of the three-dimensional human body model to be generated.
• the biological model generating device 100 may be configured to calculate multiple estimated values so that the multiple shoulder width estimates corresponding to the height and weight of a specific human body obtained in the processing of step ST1 have a distribution of variation corresponding to statistical data, depending on the use of the three-dimensional human body model to be generated.
• the biological model generation device 100 After performing the processing of step ST2, the biological model generation device 100 generates biological model information representing a three-dimensional model of the human body based on the value of the first parameter acquired in the processing of step ST1 and the estimated value of the second parameter calculated in the processing of step ST2 (step ST3). For example, in this processing, the biological model generation device 100 generates biological model information representing a three-dimensional model of the human body having the height, shoulder width, arm length, and leg length based on the height and weight of the human body acquired in the processing of step ST1 and the estimated values of shoulder width, arm length, and leg length calculated in the processing of step ST2.
• the biological model generation device 100 After performing the processing of step ST3, the biological model generation device 100 generates virtual environment information, which is information obtained by converting the three-dimensional model, based on the biological model information generated in the processing of step ST3 (step ST4). For example, in this processing, the biological model generation device 100 generates virtual environment information, which is information indicating one or more pieces of planar image data obtained by converting one or more three-dimensional models, based on the biological model information generated in the processing of step ST3.
• the biological model generating device 100 After performing the processing of step ST4, the biological model generating device 100 outputs the generated virtual environment information to an external device (step ST5) and ends the processing.
• the biological model generating device 100 includes a parameter acquiring unit 21 that acquires the value of a first parameter related to the external shape of a specific living organism; an estimation unit 22 that calculates an estimate of a second parameter indicating the external shape of the living organism corresponding to the value of the first parameter based on statistical data related to the external shapes of multiple living organisms of the same type as the specific living organism and the value of the first parameter acquired by the parameter acquiring unit 21; and a biological model generating unit 30 that generates a three-dimensional model of the living organism corresponding to the value of the first parameter and the estimated value of the second parameter based on the value of the first parameter acquired by the parameter acquiring unit 21 and the estimated value of the second parameter calculated by the estimation unit 22.
• the biological model generating device 100 calculates an estimate of a second parameter indicating the external shape of a living organism based on statistical data relating to the external shape of the living organism and the value of a first parameter of the living organism, and generates a three-dimensional model of the living organism based on the value of the first parameter and the calculated estimate of the second parameter.
• This makes it possible to generate a three-dimensional model of the living organism with a more natural external shape than when a three-dimensional model is generated based only on the value of the first parameter.
• an unnatural external shape refers to, for example, an external shape in which the dimensions themselves or the balance between the dimensions of multiple locations significantly deviate from a standard body type determined based on statistical data.
• the biological model generation device 100 according to embodiment 1 can generate a large number of three-dimensional models of living organisms with natural external shapes based on a large number of combinations of a small number of parameters.
• the biological model generation device 100 according to embodiment 1 can generate 100 three-dimensional models of living organisms with natural external shapes based on 100 different combinations of height and weight. This makes it possible to efficiently perform simulations such as image recognition simulations, physical simulations, and radio wave simulations using a large number of three-dimensional models of living organisms with different external shapes.
• the height and weight of a human body are described as examples of the first parameters, but this is not limiting.
• the first parameters may be any parameters related to the external shape of a living body.
• the first parameter may be a parameter indicating whether the living body falls into a body type classification such as thin, obese, or standard.
• the biological model generating device 100 is configured to acquire from the storage unit 25 the statistical data used when calculating the estimated value of the second parameter, but this is not limited to this.
• the biological model generating device only needs to be configured so that the estimation unit calculates an estimated value of the second parameter indicating the external shape of a living organism corresponding to the value of the first parameter based on statistical data related to the external shapes of multiple living organisms and the value of the first parameter acquired by the parameter acquisition unit.
• the statistical data may be configured to be acquired from an input device via the input unit when calculating the estimated value of the second parameter.
• the biological model generation device 100 is configured to output planar image data as virtual environment information from the output unit 50 to an external device, but this is not limited to this.
• the biological model generation device only needs to be configured to output information generated based on a three-dimensional model from the output unit to an external device as virtual environment information; for example, the biological model generation device may be configured to output three-dimensional information as virtual environment information.
• virtual environment information output as three-dimensional information can be used for three-dimensional simulations such as physical simulations and radio wave simulations.
• the biological model generation device outputs planar image data as virtual environment information, it may be configured to output it as information different from information generally obtained by human vision, such as a distance image.
• Embodiment 2 Next, a biological model generating device according to embodiment 2 will be described with reference to Fig. 7.
• the biological model generating device according to embodiment 2 differs from the biological model generating device 100 according to embodiment 1 in the configuration of the parameter estimation unit, but other configurations are similar. Therefore, the same components as those in embodiment 1 are denoted by the same reference numerals and names, and description thereof will be omitted.
• FIG. 7 is a block diagram showing the configuration of the parameter estimation unit 120 according to embodiment 2.
• the parameter estimation unit 120 according to embodiment 2 includes a parameter acquisition unit 21, a first estimation unit 22, a second estimation unit 23, a third estimation unit 24, and a storage unit 25.
• the first estimation unit 22 has the same function as the estimation unit according to embodiment 1, but differs in name, and will therefore be described using the same reference numeral as the estimation unit according to embodiment 1.
• the first estimation unit 22, the second estimation unit 23, and the third estimation unit 24 calculate different estimates of second parameters based on statistical data on the external shapes of multiple living organisms and the value of a specific first parameter acquired by the parameter acquisition unit 21. For example, based on statistical data on the height and weight of a human body and the height and weight of a specific human body, the first estimation unit 22 calculates an estimate of shoulder width corresponding to the height and weight, the second estimation unit 23 calculates an estimate of arm length corresponding to the height and weight, and the third estimation unit 24 calculates an estimate of leg length corresponding to the height and weight. Note that the number of estimation units included in the parameter estimation unit is not limited to two or three, and the parameter estimation unit may be configured to calculate different estimates of second parameters using four or more estimation units.
• Embodiment 3 Next, a biological model generating device according to embodiment 2 will be described with reference to Fig. 8.
• the biological model generating device according to embodiment 2 differs from the biological model generating device 100 according to embodiment 1 in the configuration of the parameter estimation unit, but other configurations are the same. Therefore, the same components as those in embodiment 1 are denoted by the same reference numerals and names, and description thereof will be omitted.
• FIG. 8 is a block diagram showing the configuration of the parameter estimation unit 220 according to embodiment 3.
• the parameter estimation unit 220 according to embodiment 3 has a parameter acquisition unit 21, a first estimation unit 22, a second estimation unit 223, and a storage unit 25.
• the first estimation unit 22 has the same function as the estimation unit according to embodiment 1, but differs in name, and will therefore be described using the same reference numeral as the estimation unit according to embodiment 1.
• the first estimation unit 22 calculates an estimated value of a first second parameter based on statistical data related to the external shapes of multiple living organisms and the value of a specific first parameter acquired by the parameter acquisition unit 21.
• the second estimation unit 223 calculates an estimated value of a second second parameter that is correlated with the value of the first second parameter based on the statistical data and the calculation result of the estimated value by the first estimation unit 22.
• the first estimation unit 22 calculates an estimated value of arm length as the first second parameter based on statistical data related to the external shapes of multiple living organisms and the height and weight of a human body.
• the second estimation unit 223 calculates an estimated value of forearm length as the second second parameter based on statistical data indicating the relationship between arm length and forearm length and the calculation result of the arm length estimate by the first estimation unit 22.
• the biological model generation device is able to calculate estimates of second parameters that are more natural than when the estimates of multiple second parameters are calculated individually.
• the biological model generating device according to embodiment 2 has a different configuration of a parameter estimation unit compared to the biological model generating device 100 according to embodiment 1, but other configurations are the same. Therefore, the same components as those in embodiment 1 are denoted by the same reference numerals and names, and description thereof will be omitted.
• FIG. 9 is a block diagram showing the configuration of the parameter estimation unit 320 according to embodiment 4.
• the parameter estimation unit 320 according to embodiment 4 includes a parameter acquisition unit 21, a first estimation unit 22, a second estimation unit 323, and a storage unit 25.
• the first estimation unit 22 has the same function as the estimation unit according to embodiment 1, but differs in name, and will therefore be described using the same reference numeral as the estimation unit according to embodiment 1.
• the first estimation unit 22 calculates an estimated value of a first second parameter based on statistical data related to the external shapes of multiple living organisms and the value of a specific first parameter acquired by the parameter acquisition unit 21.
• the second estimation unit 323 calculates an estimated value of a second second parameter correlated with the value of the first second parameter based on the statistical data, the value of the specific first parameter, and the calculation result of the estimated value by the first estimation unit 22.
• the first estimation unit 22 calculates an estimated value of arm length as the first second parameter based on statistical data related to the external shapes of multiple living organisms and the height and weight of the human body.
• the second estimation unit 223 calculates an estimated value of leg length as the second second parameter based on statistical data indicating the relationship between arm length and leg length, the height and weight of the human body, and the calculation result of the leg length estimate by the first estimation unit 22.
• the biological model generation device is able to calculate an estimate of the second parameter that is more natural than when the estimates of multiple second parameters are calculated individually, even when the correlation between the first second parameter and the second second parameter is not strong enough to allow the estimate of the second second parameter to be calculated using only the estimate of the first second parameter.
• Embodiment 5 Next, a biological model generating device according to embodiment 2 will be described with reference to Fig. 10.
• the biological model generating device according to embodiment 2 differs from the biological model generating device 100 according to embodiment 1 in the configuration of the parameter estimation unit, but other configurations are the same. Therefore, the same components as those in embodiment 1 are denoted by the same reference numerals and names, and description thereof will be omitted.
• FIG. 10 is a block diagram showing the configuration of the parameter estimation unit 420 according to embodiment 5.
• the parameter estimation unit 420 according to embodiment 5 includes a parameter acquisition unit 21, an estimation unit 22, a determination unit 26, and a storage unit 25.
• the determination unit 26 determines whether either or both of the value of the first parameter acquired by the parameter acquisition unit 21 and the estimated value of the second parameter calculated by the estimation unit 22 are appropriate values for generating a three-dimensional model of a living organism. For example, if the value of the first parameter acquired by the parameter acquisition unit 21 is outside a preset range, the determination unit 26 determines that the value of the first parameter is inappropriate. For example, if the living organism of the three-dimensional model generated by the biological model generation device 100 is a human body, the determination unit 26 determines that the value of the first parameter is inappropriate based on a first parameter value of 10 cm for height.
• the determination unit 26 determines that the value of the first parameter is inappropriate. Specifically, when the value of the first first parameter and the value of the second first parameter are acquired by the parameter acquisition unit 21, the determination unit 26 determines that the value of the first parameter is inappropriate if the value of the second first parameter is outside the range of the second first parameter set based on the value of the first first parameter.
• the range of values of the first parameter used to determine whether the value of the first parameter acquired by the parameter acquisition unit 21 is an appropriate value is set in advance based on, for example, a range that is considered natural for the external shape of a living organism.
• the range of values of the first parameter may also be set based on other conditions. For example, if a sufficient number of samples of statistical data for a second parameter corresponding to a specific first parameter value have not been collected, and an estimated value of the second parameter is calculated based on the statistical data and the value of the first parameter, the calculated estimated value of the second parameter may be an unnatural value indicating the external shape of a living organism.
• the range of values of the first parameter used to determine whether the value of the first parameter acquired by the parameter acquisition unit 21 is an appropriate value may be set based on a range in which a sufficient number of samples of statistical data are considered to be sufficient for calculating an estimated value of the second parameter.
• the judgment unit 26 judges that the value of the second parameter is not an appropriate value. Further, for example, if the relationship between the value of the first parameter acquired by the parameter acquisition unit 21 and the estimated value of the second parameter calculated by the estimation unit 22 is not a predetermined relationship, the judgment unit 26 judges that the estimated value of the second parameter is not an appropriate value. Specifically, if the estimated value of the second parameter calculated by the estimation unit 22 is a value that exceeds the range of the second parameter that is set based on the value of the first parameter acquired by the parameter acquisition unit 21, the judgment unit 26 judges that the value of the second parameter is not an appropriate value.
• the determination unit 26 determines that the estimated value of the second parameter is inappropriate based on the relationship between the estimated value of sitting height as the second parameter calculated by the estimation unit 22 being 100 cm and the height as the first parameter acquired by the parameter acquisition unit 21 being 120 cm.
• the biological model generation device generates a three-dimensional model of the living organism based on the determination result of the determination unit 26. For example, if the determination unit 26 determines that the value of the first parameter does not exceed a preset range, the biological model generation device according to the fifth embodiment generates a three-dimensional model of the living organism corresponding to the value of the first parameter and the estimated value of the second parameter, and if the determination unit 26 determines that the value of the first parameter exceeds the range, the biological model generation device does not generate a three-dimensional model of the living organism corresponding to the value of the first parameter and the estimated value of the second parameter.
• the biological model generation device determines that the value of the second first parameter does not exceed a range that is preset based on the value of the first first parameter, the biological model generation device generates a three-dimensional biological model corresponding to the value of the first first parameter, the value of the second first parameter, and the estimated value of the second parameter, and if the determination unit 26 determines that the value of the second first parameter exceeds the above range, the biological model generation device does not generate a three-dimensional biological model corresponding to the value of the first first parameter, the value of the second first parameter, and the estimated value of the second parameter.
• the output unit 50 outputs the three-dimensional model generated by the biological model generation unit 30 to an external device, and if the determination unit 26 determines that the value of the first parameter exceeds the above-mentioned range, the output unit 50 does not output the three-dimensional model generated by the biological model generation unit 30.
• the output unit 50 outputs the three-dimensional model generated by the biological model generation unit 30 to an external device, and if the determination unit 26 determines that the value of the second first parameter exceeds the above-mentioned range, the output unit 50 does not output the three-dimensional model generated by the biological model generation unit 30.
• the biological model generating device of embodiment 5 determines that either or both of the value of the first parameter acquired by the parameter acquisition unit 21 and the estimated value of the second parameter calculated by the estimation unit 22 are not appropriate values for generating a three-dimensional model of a living organism, it outputs a signal indicating the determination result.
• the biological model generating device determines that either or both of the value of the first parameter acquired by the parameter acquisition unit 21 and the estimated value of the second parameter calculated by the estimation unit 22 are not appropriate values for generating a three-dimensional model of a living organism, it outputs a signal indicating the determination result to an alarm unit (not shown), and notifies the user of the determination result by the alarm unit.
• the alarm unit may be configured with a speaker that emits sound based on a signal input, a display device that displays an image based on a signal input, a light-emitting device that changes the light emission pattern based on a signal input, etc.
• the biological model generation device determines that either or both of the value of the first parameter acquired by the parameter acquisition unit 21 and the estimated value of the second parameter calculated by the estimation unit 22 are not appropriate values for generating a three-dimensional model of a living organism, it outputs a signal indicating the determination result to an external device and notifies the user of the external device of the determination result.
• the biological model generation device is configured to use the determination unit 26 to determine whether either or both of the value of the first parameter acquired by the parameter acquisition unit 21 and the estimated value of the second parameter calculated by the estimation unit 22 are appropriate values for generating a three-dimensional model of the living organism.
• the biological model generation device only needs to be configured to determine the appropriateness of the values acquired in any of the processes so that the three-dimensional model of the living organism to be generated is appropriate.
• the biological model generation device may be configured such that the estimation unit acquires an index of variation of the second parameter of the living organism corresponding to the value of the first parameter based on statistical data of the second parameter, and the biological model generation unit generates a three-dimensional model of the living organism if the index of variation is a value indicating smaller variation than a preset value, and does not generate a three-dimensional model of the living organism if the index of variation is a value indicating larger variation than the preset value.
• the biological model generation device may be configured such that if the index of variation of the second parameter of the living organism corresponding to the value of the first parameter, obtained based on statistical data of the second parameter, is a value indicating smaller variation than a preset value, the output unit outputs a three-dimensional model of the living organism, and if the index of variation is a value indicating larger variation than a preset value, the output unit does not output a three-dimensional model of the living organism.
• the biological model generation device, biological model generation program, and biological model generation method disclosed herein can be used, for example, to generate a three-dimensional model of a living organism based on the values of specific parameters.
• a parameter acquisition unit that acquires a value of a first parameter related to the external shape of a specific living body; an estimation unit that calculates an estimated value of a second parameter that indicates the outer shape of a living body corresponding to the value of the first parameter based on statistical data regarding the outer shapes of multiple living bodies of the same type as the specific living body and the value of the first parameter acquired by the parameter acquisition unit; and a biological model generation unit that generates a three-dimensional model of a living organism corresponding to the value of the first parameter and the estimated value of the second parameter, based on the value of the first parameter acquired by the parameter acquisition unit and the estimated value of the second parameter calculated by the estimation unit.
• the estimation unit calculates, based on the value of the first parameter, an estimated value of a second parameter for each of two or more living organisms corresponding to the value of the first parameter;
• the biological model generation device according to claim 1, wherein the biological model generation unit generates three-dimensional models of two or more living organisms corresponding to the value of the first parameter and the estimated value of the second parameter of each of the two or more living organisms.
• (Appendix 3) 3.
• Appendix 4 4.
• the biological model generating device wherein the estimation unit calculates the second parameter as an estimated value in accordance with a distribution of variation indicated by the statistical data.
• the parameter acquisition unit acquires a value of a first first parameter and a value of a second first parameter related to an external shape of the specific living body;
• the biological model generation device according to any one of appendices 1 to 4, wherein the estimation unit calculates an estimated value of the second parameter indicating an external shape of the living body corresponding to the value of the first first parameter and the value of the second first parameter based on the statistical data, the value of the first first parameter, and the value of the second first parameter.
• the first parameter is a parameter related to a body length of the specific living organism
• the biological model generating device according to any one of claims 1 to 5, wherein the second first parameter is a parameter relating to a body type of the specific living organism.
• the first parameter is a parameter indicating a height of the specific living body, 7.
• the biological model generating device according to claim 1, wherein the second first parameter is a parameter indicating a weight of the specific living organism.
• the estimation unit acquires an index of variation of a second parameter of the living body corresponding to the value of the first parameter based on the statistical data;
• the biological model generation device according to any one of appendixes 1 to 10, characterized in that, when the index of variation is a value indicating smaller variation than a preset value, the biological model generation unit generates a three-dimensional model of the living body corresponding to the value of the first parameter and the estimated value of the second parameter, and when the index of variation is a value indicating larger variation than a preset value, the biological model generation unit does not generate a three-dimensional model of the living body corresponding to the value of the first parameter and the estimated value of the second parameter.
• Appendix 12 an output unit that outputs the three-dimensional model generated by the biological model generation unit;
• the biological model generation device according to any one of appendixes 1 to 11, characterized in that the output unit outputs the three-dimensional model of the organism generated by the biological model generation unit when an index of variation of a second parameter of the organism corresponding to the value of the first parameter, obtained based on the statistical data, is a value indicating smaller variation than a preset value, and does not output the three-dimensional model of the organism generated by the biological model generation unit when the index of variation is a value indicating larger variation than a preset value.
• the biological model generating device converts the three-dimensional model generated by the biological model generating unit into two-dimensional image data viewed from a specific viewpoint. (Appendix 17) 17.
• the biological model generating device according to claim 16, wherein the three-dimensional model conversion unit generates two-dimensional image data including images of the three-dimensional model generated by the biological model generating unit and objects existing around the three-dimensional model. 17.
• the biological model generating device according to any one of claims 1 to 16.
• Appendix 18 The biological model generation device according to any one of appendices 1 to 17, wherein the estimation unit calculates an estimated value of a second parameter indicating an external shape of a living organism corresponding to the value of the first parameter using a trained model, based on the value of the first parameter.
• a parameter acquisition unit that acquires a value of a first parameter related to the external shape of a specific living body
• an estimation unit that calculates an estimated value of a second parameter that indicates the outer shape of a living body corresponding to the value of the first parameter based on statistical data regarding the outer shapes of multiple living bodies of the same type as the specific living body and the value of the first parameter acquired by the parameter acquisition unit
• a biological model generation unit that generates a three-dimensional model of a living organism corresponding to the value of the first parameter and the estimated value of the second parameter, based on the value of the first parameter acquired by the parameter acquisition unit and the estimated value of the second parameter calculated by the estimation unit.
• Input unit (parameter acquisition unit), 20 Parameter estimation unit, 21 Parameter acquisition unit, 22 Estimation unit (first estimation unit), 23 Second estimation unit, 24 Third estimation unit, 25 Memory unit, 26 Determination unit, 30 Biological model generation unit, 40 Virtual environment generation unit (conversion unit), 50 Output unit, 100 Biological model generation device, 120 Parameter estimation unit, 220 Parameter estimation unit, 223 Second estimation unit, 320 Parameter estimation unit, 323 Second estimation unit, 420 Parameter estimation unit.

Landscapes

• Engineering & Computer Science (AREA)
• Software Systems (AREA)
• Theoretical Computer Science (AREA)
• General Physics & Mathematics (AREA)
• General Engineering & Computer Science (AREA)
• Physics & Mathematics (AREA)
• Evolutionary Computation (AREA)
• Medical Informatics (AREA)
• Computing Systems (AREA)
• Data Mining & Analysis (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Mathematical Physics (AREA)
• Artificial Intelligence (AREA)
• Computer Graphics (AREA)
• Computer Hardware Design (AREA)
• Image Analysis (AREA)

Priority Applications (2)

Applications Claiming Priority (1)

Publications (1)

Family

ID=96920176

Family Applications (1)

Country Status (2)

Citations (4)

• 2024
  • 2024-02-29 WO PCT/JP2024/007462 patent/WO2025181988A1/ja active Pending
  • 2024-02-29 JP JP2026503386A patent/JPWO2025181988A1/ja active Pending

Patent Citations (4)

Also Published As

Similar Documents

Legal Events