JP2021178468A - Modeling data generation device, modeling data generation method, and modeling data generation program - Google Patents

Abstract

To provide a modeling data generation device, a modeling data generation method, and a modeling data generation program capable of generating modeling data for three-dimensional modeling from an image of a two-dimensional shoe mark in a simple configuration.SOLUTION: A modeling data generation device comprises: a three-dimensional model generation section 312 for generating a three-dimensional model according to a shoe mark of a two-dimensional image including the shoe mark; and a modeling data generation section 313 for generating three-dimensional modeling data for modeling the shoe mark by fitting polyhedral data to the generated three-dimensional model.SELECTED DRAWING: Figure 3

Description

The present embodiment relates to a modeling data generation device, a modeling data generation method, and a modeling data generation program.

Footprint appraisal is known as one of the forensics. Footprint appraisal is an investigation method that identifies the person in the footsteps from the footsteps and footsteps left on the scene and estimates what happened on the spot. It is necessary to collect footprints for footprint identification. As a method of collecting footprints, for example, a method of pouring plaster to collect a last is known. However, the method using gypsum takes time to collect, and it is difficult to collect the details of the footprints. On the other hand, in recent years, mainly in the apparel field, a method of measuring the shape of a foot using a digital device and forming a foot tree shape from the measured data has been proposed, for example, as proposed in Patent Document 1. It's coming.

International Publication No. 2017/078168

The image obtained for the last collection is usually a two-dimensional image. Therefore, there is a demand for a method for generating modeling data for modeling a three-dimensional last from an image of a two-dimensional shoe mark.

This embodiment is made in view of the above circumstances, and is a modeling data generation device, a modeling data generation method, and a modeling data generation device capable of generating modeling data for three-dimensional modeling from an image of a two-dimensional shoe mark with a simple configuration. The purpose is to provide a modeling data generation program.

The modeling data generation device of the first aspect has a three-dimensional model generation unit that generates a three-dimensional model corresponding to the shoe marks of a two-dimensional image including shoe marks, and the generated three-dimensional model is fitted with polyhedron data. It is provided with a modeling data generation unit that generates three-dimensional modeling data for modeling a shoe mold.

The modeling data generation device of the second aspect has a three-dimensional model generation unit that generates a three-dimensional model according to the shoe marks of the two-dimensional image including the shoe marks, and shoes similar to the shoe sole of the generated three-dimensional model. A search unit that searches for a shoe model that is a 3D model of shoes with a sole, and a generated 3D model that fits the searched shoe model to generate 3D modeling data for shoe model modeling. It is provided with a modeling data generation unit.

The modeling data generation method of the third aspect is to generate a three-dimensional model corresponding to the shoe marks of the two-dimensional image including the shoe marks, and to fit the polyhedral data to the generated three-dimensional model to fit the shoe type. It comprises generating three-dimensional modeling data for modeling.

The modeling data generation method of the fourth aspect is to generate a three-dimensional model corresponding to the shoe mark of the two-dimensional image including the shoe mark, and a shoe having a shoe sole similar to the shoe sole of the generated three-dimensional model. It includes searching for a shoe model, which is a 3D model of the above, and fitting the searched shoe model to the generated 3D model to generate 3D modeling data for shoe model modeling. do.

The modeling data generation program of the fifth aspect generates a three-dimensional model corresponding to the shoe marks of the two-dimensional image including the shoe marks, and fits the polyhedron data to the generated three-dimensional model to fit the shoe type. Have the computer perform the generation of 3D modeling data for modeling.

The modeling data generation program of the sixth aspect generates a three-dimensional model corresponding to the shoe mark of the two-dimensional image including the shoe mark, and the shoe having a shoe sole similar to the shoe sole of the generated three-dimensional model. Searching for a shoe model, which is a 3D model of, and fitting the searched shoe model to the generated 3D model to generate 3D modeling data for shoe mold modeling. To execute.

According to the present invention, it is possible to provide a modeling data generation device, a modeling data generation method, and a modeling data generation program that can generate modeling data for three-dimensional modeling from an image of a two-dimensional shoe mark with a simple configuration.

FIG. 1 is a diagram showing an example of a configuration of a modeling data generation system including the modeling data generation device of the first embodiment. FIG. 2 is a diagram showing a configuration of an example of a modeling data generation device. FIG. 3 is a functional block diagram of the processor of the first embodiment. FIG. 4A is a conceptual diagram of the fitting of the first embodiment. FIG. 4B is a conceptual diagram of the fitting of the first embodiment. FIG. 5 is a flowchart for explaining the operation of the modeling data generation device according to the first embodiment. FIG. 6 is a functional block diagram of the processor of the second embodiment. FIG. 7A is a conceptual diagram of the fitting of the second embodiment. FIG. 7B is a conceptual diagram of the fitting of the second embodiment. FIG. 8 is a flowchart for explaining the operation of the modeling data generation device according to the second embodiment.

Hereinafter, embodiments will be described with reference to the drawings.
[First Embodiment]
FIG. 1 is a diagram showing an example of a configuration of a modeling data generation system including the modeling data generation device of the first embodiment. As shown in FIG. 1, the modeling data generation system 1 includes a camera 2, a modeling data generation device 3, and a three-dimensional (3D) printer 4. The camera 2, the modeling data generation device 3, and the 3D printer 4 can communicate with each other via, for example, a network N. The camera 2 and the 3D printer 4 do not necessarily have to be able to communicate with the modeling data generation device 3 via the network N. The camera 2 may be configured so that the two-dimensional image can be transferred to the modeling data generation device 3. Further, the 3D printer 4 may be configured so as to be able to receive modeling data from the modeling data generation device 3.

The camera 2 is, for example, a digital camera that captures a subject and generates a two-dimensional image of the subject. Here, the subject in the embodiment is a shoe mark attached to the ground. The configuration of the camera 2 is not particularly limited as long as it can generate a two-dimensional image. Further, the camera 2 may be provided in various terminals such as smartphones.

The modeling data generation device 3 obtains three-dimensional modeling data for three-dimensional modeling of the shoe marks based on a three-dimensional model including the shoe marks generated from the two-dimensional image including the shoe marks generated by the camera 2. Generate.

The 3D printer 4 forms a last based on the modeling data. A laser method or the like is used for the configuration of the 3D printer 4, but the configuration is not particularly limited. Further, as the modeling material used for modeling, for example, gypsum powder may be used when the last is modeled with gypsum. Further, in order to reproduce the same texture as shoes, a rubber-like material having thermoplasticity such as TPU (thermoplastic polyurethane) may be used.

FIG. 2 is a diagram showing a configuration of an example of a modeling data generation device 3. The modeling data generation device 3 of FIG. 2 includes a processor 31, a ROM 32, a RAM 33, a storage 34, an input interface 35, an output interface 36, and a communication interface 37. Each of these is connected to each other via a bus 38. The modeling data generation device 3 may be an electronic device such as a personal computer (PC), a tablet terminal, or a smartphone.

The processor 31 is a processor that controls various operations of the modeling data generation device 3. The processor 31 is, for example, a CPU, but is not limited thereto. The processor 31 may be an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), a GPU (Graphic Processing unit), or the like. Further, the processor 31 does not necessarily have to be composed of one CPU or the like, and may be composed of a plurality of CPUs or the like.

The ROM 32 stores a startup program and the like of the modeling data generation device 3. The RAM 33 is a main storage device for the processor 31 and the like.

The storage 34 is a storage such as a hard disk or a solid state drive.

The storage 34 stores various programs, parameters, and the like necessary for controlling the modeling data generation device 3 used by the processor 31. These various programs include a modeling data generation program. The modeling data generation program will be described in detail later.

Further, polyhedral data is stored in the storage 34. The polyhedral data is a polyhedron for generating modeling data, for example, a rectangular parallelepiped data structure. The polyhedral data has coordinate information in the shape of a polyhedron.

Here, the data stored in the storage 34 may be stored in a storage separate from the modeling data generation device 3.

The input interface 35 includes a keyboard, a mouse, a touch panel, and the like. In response to the user's operation via the input interface 35, a signal indicating the content of the user's operation is input to the processor 31 via the bus 38. The processor 31 executes various processes according to the signal indicating the content of this operation.

The output interface 36 includes, for example, an output device such as a liquid crystal display and an interface for communication with these output devices. The output interface 36 sends image data to the display at an appropriate timing, for example, when displaying an image on the display.

The communication interface 37 includes an interface for communication with the camera 2 and the 3D printer 4. The communication interface 37 may include an interface for communication by wired communication, or may include an interface for communication by wireless communication.

FIG. 3 is a functional block diagram of the processor 31 of the first embodiment. The processor 31 includes an image acquisition unit 311, a three-dimensional model generation unit 312, a modeling data generation unit 313, and a control unit 314. The image acquisition unit 311, the three-dimensional model generation unit 312, the modeling data generation unit 313, and the control unit 314 are realized, for example, by the processor 31 executing various programs stored in the storage 34. The image acquisition unit 311, the three-dimensional model generation unit 312, the modeling data generation unit 313, and the control unit 314 may be realized by hardware that performs the same processing as each.

Further, the image acquisition unit 311, the three-dimensional model generation unit 312, the modeling data generation unit 313, and the control unit 314 do not all need to be realized by the processor 31. For example, either the three-dimensional model generation unit 312 or the modeling data generation unit 313 may be provided on a server different from the modeling data generation device 3.

The image acquisition unit 311 acquires an image from the camera 2. This image is two or more images generated by taking an object including a shoe mark from a plurality of different directions with the camera 2. Depending on the three-dimensional model generation method by the three-dimensional model generation unit 312, the image acquisition unit 311 may be configured to acquire one image.

The 3D model generation unit 312 generates a 3D model of the shoe mark from the 2D image including the shoe mark acquired by the image acquisition unit 311. The 3D model generation unit 312 generates a 3D model using, for example, MVS (Multi-View Stereo). MVS is a method of estimating the 3D shape of an object from the correspondence between the coordinates of the feature points of a common object (shoe mark) in 2D images taken from multiple different directions and the internal parameters of the camera. Is. When the 3D model generator 312 is configured to generate a 3D model of an object by MVS, the camera 2 has two or more images taken from different directions and the inside of the camera at the time of each shooting. The parameters are sent to the modeling data generation device 3.

Further, the 3D model generation unit 312 may be configured to generate a 3D model of the object by using SfS (Shape from Shading). SfS is a method of estimating the three-dimensional shape of an object from the shadow in a two-dimensional image. When the 3D model generation unit 312 is configured to generate a 3D model of the object by SfS, the camera 2 may send one image. Further, when the 3D model generation unit 312 is configured to generate a 3D model of the object by SfS, the 3D model generation unit 312 recognizes the shadow in the image by using deep learning. May be good. Further, the 3D model generation unit 312 may generate a 3D model by combining MVS and SfS.

The modeling data generation unit 313 of the first embodiment generates modeling data by fitting the polyhedral data stored in the storage 34 to the three-dimensional model generated by the three-dimensional model generation unit 312.

4A and 4B are conceptual diagrams of the fitting of the first embodiment. The fitting is performed by bringing a part of the polyhedral data D1 close to the surface of the shoe mark in the three-dimensional model M as shown in FIG. 4A, and then deforming the surface F1 of the polyhedral data D1 as shown in FIG. 4B. Will be done. The deformation of the surface F1 of the polyhedral data D1 is performed, for example, by moving each point constituting the surface F1 in the normal direction of the surface F1. Further, the deformation of the surface F1 of the polyhedral data D1 may be performed by non-rigid body alignment. The polyhedral data D1 fitted as shown in FIG. 4B is the modeling data.

The control unit 314 controls when the modeling data generated by the modeling data generation unit 313 is transmitted to the 3D printer 4 via the communication interface 37.

Next, the operation of the modeling data generation device 3 will be described. FIG. 5 is a flowchart for explaining the operation of the modeling data generation device 3 in the first embodiment. The process of FIG. 5 is performed by, for example, the processor 31 according to the modeling data generation program. Prior to the operation of the modeling data generation device 3, the user of the camera 2 photographs the shoe marks. Here, in order to facilitate the modeling of the last in the 3D printer 4, the size of the modeling data generated by the modeling data generation unit 313 may be aligned with the size of the last modeled in the 3D printer 4. desirable. For this purpose, it is desirable that the size of the shoe mark to be photographed is known. In order to make the size of the shoe mark to be photographed known, the user of the camera 2 photographs the shoe mark together with a marker of the known size. The marker is not limited as long as the size is known and can be identified on the image. Alternatively, the user of the camera 2 may shoot with the angle of view of the camera 2, that is, the shooting distance and the focal length fixed. Further, the user of the camera 2 may measure the size of the shoe mark and input the measured size of the shoe mark to the modeling data generation device 3 together with the captured image. After the shooting is completed in this way, the user sends the image shot by the camera 2 to the modeling data generation device 3 via, for example, the network N.

In step S1, the processor 31 determines whether or not an image has been input. When it is determined in step S1 that no image has been input, the processor 31 ends the process of FIG. When it is determined in step S1 that the image has been input, the process proceeds to step S2.

In step S2, the processor 31 detects deposits on the shoe marks in the image. The deposits are those in which fallen leaves, gum, etc., which had adhered to the sole of the shoe are transferred to the ground, or those that have adhered after the formation of shoe marks. The deposit can be detected by extracting the region of the shoe mark in the image by, for example, edge extraction, and detecting the feature amount in the extracted region.

In step S3, the processor 31 determines whether or not the deposit has been detected. When it is determined that the deposit is detected, the process proceeds to step S4. When it is determined that no deposit is detected, the process proceeds to step S5.

In step S4, the processor 31 sets the position of the deposit in the image at the defect location. Alternatively, in step S4, the processor 31 complements the position of the deposit in the image with the image around it.

In step S5, the processor 31 generates a three-dimensional model of the shoe mark. Here, the processor 31 does not have to generate a three-dimensional model for the position set in the defective portion. Alternatively, the processor 31 may generate a three-dimensional model including the position set in the defective portion, and remove the portion corresponding to the defective portion from the generated three-dimensional model. Alternatively, the processor 31 may generate a three-dimensional model including the position set in the defective portion, and complement the portion corresponding to the defective portion in the generated three-dimensional model from the surrounding data. The deposits are removed or complemented prior to the generation of the build data because they are parts that are not needed for the build.

In step S6, the processor 31 generates modeling data. As described above, the processor 31 generates modeling data by fitting the polyhedral data so as to match the generated three-dimensional model of the shoe mark.

In step S7, the processor 31 transmits the modeling data to the 3D printer 4. After that, the processor 31 ends the process of FIG. As a result, the 3D printer 4 forms the last based on the modeling data.

As described above, according to the first embodiment, a three-dimensional model of shoe marks is generated from a two-dimensional image including shoe marks, and modeling data is generated by fitting polyhedral data to this three-dimensional model. .. That is, in the first embodiment, a three-dimensional model can be generated only by the camera function mounted on a digital camera, a smartphone, or the like. In addition, the camera function installed in a digital camera, a smartphone, or the like can capture an image with a higher resolution than a 3D scanner. As a result, a finer three-dimensional model can be generated with a simple configuration. Further, in the first embodiment, modeling is performed from the modeling data by a 3D printer. Since it is not necessary to model the last on site, the labor required for transporting the modeling material such as plaster can be reduced. Further, if it is a 3D printer, various materials such as gypsum and TPU can be used. For example, by performing modeling with plaster, a last that is similar to conventional foot pattern collection can be formed. Further, in the case of TPU, a last having the same texture as the original shoe can be formed. For this reason, it becomes easy to reproduce the same situation as the site where the shoe mark was actually found.

[Second Embodiment]
Next, the second embodiment will be described. In the first embodiment, the last modeling data is generated by fitting the polyhedral data to the three-dimensional model. On the other hand, in the second embodiment, the modeling data of the last is generated by fitting the sole portion of the shoe model, which is the 3D model of the last, to the 3D model generated based on the 2D image. Will be done. Here, the same configuration as that of the first embodiment can be applied to the basic configuration of the modeling data generation system and the modeling data generation device 3. Therefore, in the following, only the differences between the first embodiment and the second embodiment will be described.

Data of various shoe models are stored in the storage 34 of the second embodiment. The shoe model data includes a three-dimensional model generated based on various shoes and feature quantity data extracted from the three-dimensional model. Here, the shoe in the embodiment means a new shoe without scratches, stains, or deformation, such as a shoe at the time of product shipment. Further, the shoe model may include at least a sole portion. The feature amount data may be arbitrary data, and may include, for example, PFH (Point Feature Histogram) and SHOT (Signature of Histograms of OrienTations). In addition, the shoe model data may include data such as the shooting time of the image used for generating the three-dimensional model, the shooting location, the shoe manufacturer name, and the product number as supplementary data. Further, the storage 34 may store the engraved data and supplementary data of the engraved data. The stamp here is a stamp indicating the manufacturer name or the like of the shoe provided on the sole. The engraved data may be image data obtained by photographing various soles, or may be text data written on the engraved.

FIG. 6 is a functional block diagram of the processor 31 of the second embodiment. The processor 31 has an image acquisition unit 311, a three-dimensional model generation unit 312, a modeling data generation unit 313, a control unit 314, and a search unit 315. The image acquisition unit 311, the three-dimensional model generation unit 312, and the control unit 314 are the same as those in the first embodiment.

The search unit 315 uses the three-dimensional model generated by the three-dimensional model generation unit 312 as a query for searching, and searches the storage 34 for a shoe model having a shoe sole shape similar to that of the three-dimensional model. The search unit 315 searches by, for example, the nearest neighbor search. In this case, the search unit 315 searches the storage 34 for a shoe model in which the difference between the three-dimensional models is smaller than the predetermined value, the matching degree of the feature points is higher than the predetermined value, or the distance between the feature quantities is closer than the predetermined value. do. Further, the search unit 315 may search the storage 34 for a shoe model having a mark similar to this mark, using the mark of the sole extracted from the two-dimensional image as a search query.

The modeling data generation unit 313 of the second embodiment generates modeling data by fitting the shoe model searched by the search unit 315 to the three-dimensional model generated by the three-dimensional model generation unit 312. 7A and 7B are conceptual diagrams of the fitting of the second embodiment. As shown in FIG. 7A, the fitting is performed by bringing the sole surface F2 of the shoe model D2 close to the surface of the shoe mark in the three-dimensional model M, and then the sole surface F2 of the shoe model D2 as shown in FIG. 7B. It is done by transforming. Deformation of the surface F2 of the sole is performed, for example, by moving each point constituting the surface F2 in the normal direction of the surface F2. Further, the deformation of the surface F2 of the sole may be performed by non-rigid body alignment. The shoe model D2 fitted as shown in FIG. 7B is the modeling data. This modeling data is data in a state in which the sole of the shoe reflects the wear and scratches of the sole assumed from the shoe mark restored by the three-dimensional model M.

Next, the operation of the modeling data generation device 3 will be described. FIG. 8 is a flowchart for explaining the operation of the modeling data generation device 3 in the second embodiment. The processing of FIG. 8 is performed by, for example, the processor 31 according to the modeling data generation program. Prior to the operation of the modeling data generation device 3, the user of the camera 2 photographs the shoe marks. The imaging may be performed in the same manner as in the first embodiment.

In step S11, the processor 31 determines whether or not an image has been input. When it is determined in step S11 that no image has been input, the processor 31 ends the process of FIG. When it is determined in step S11 that the image has been input, the process proceeds to step S12.

In step S12, the processor 31 detects deposits on the shoe marks in the image. The detection of deposits may be the same as in the first embodiment.

In step S13, the processor 31 determines whether or not the deposit has been detected. When it is determined that the deposit is detected, the process proceeds to step S14. When it is determined that no deposit is detected, the process proceeds to step S15.

In step S14, the processor 31 sets the position of the deposit in the image at the defect location. Alternatively, in step S14, the processor 31 complements the position of the deposit in the image with the image around it.

In step S15, the processor 31 generates a three-dimensional model of the shoe mark. Here, the processor 31 does not have to generate a three-dimensional model for the position set in the defective portion. Alternatively, the processor 31 may generate a three-dimensional model including the position set in the defective portion, and remove the portion corresponding to the defective portion from the generated three-dimensional model. Alternatively, the processor 31 may generate a three-dimensional model including the area set in the defective portion, and complement the portion corresponding to the defective portion in the generated three-dimensional model from the surrounding data. The deposits are removed or complemented prior to the generation of the build data because they are parts that are not needed for the build.

In step S16, the processor 31 searches the storage 34 for a shoe model similar to the generated three-dimensional model. Here, at the time of searching, the processor 31 uses the marker size information or the shooting distance information to align the size of the generated three-dimensional model with the size of the shoe model stored in the storage 34. .. Further, at the time of searching, the processor 31 divides the generated three-dimensional model into a plurality of parts, compares each divided part with the shoe model stored in the storage 34, and selects a shoe model having many similar parts. You may try to search. While sole wear and scratches are useful for person estimation, they are noisy when searching for similar shoe models. In addition, depending on how the original shoe marks are attached, the three-dimensional shape may not be restored to the extent that it can be compared. By comparing each part, it is possible to suppress the influence on the search due to these wears and scratches, how to make shoe marks, and the like. Further, the processor 31 may not use the position set in the missing part for the search. If the 3D model contains deposits, the deposits are different from the 3D model stored in the storage 34 at the time of retrieval. That is, depending on the presence or absence of deposits, the three-dimensional model that should be searched may not be searched. By not using the position set in the missing part for the search, the influence on the search can be suppressed.

In step S17, the processor 31 presents to the user a plurality of upper shoe models similar to the three-dimensional model as candidates for the shoe model. For example, the processor 31 displays an image of a similar shoe model on a display such as a liquid crystal display. At this time, supplementary data such as the manufacturer name and product number of the shoes associated with each shoe model may also be displayed.

In step S18, the processor 31 determines whether or not the shoe model is selected from the presented shoe model candidates. In step S18, the process waits until it is determined that the shoe model has been selected. When it is determined in step S18 that the shoe model has been selected, the process proceeds to step S19.

In step S19, the processor 31 generates modeling data using the shoe model selected by the user. As described above, the processor 31 generates modeling data by fitting the shoe model so as to match the three-dimensional model corresponding to the generated shoe mark.

In step S20, the processor 31 transmits the modeling data to the 3D printer 4. After that, the processor 31 ends the process of FIG. As a result, the 3D printer 4 forms the last based on the modeling data.

As described above, according to the second embodiment, the modeling data is generated based on the shoe model stored in advance in the storage 34. As a result, a last that is closer to the actual shoe can be formed. Further, in the second embodiment, the modeling data of the last is generated by fitting the shoe model to the three-dimensional model. As a result, it is possible to reflect the wear and scratches on the sole of the shoe, which are assumed from the shoe marks restored by the three-dimensional model, in the modeling data. Therefore, a last that is similar to the one that was actually collected can be formed.

[Modification example]
Hereinafter, modified examples of the first embodiment and the second embodiment will be described. In the first embodiment and the second embodiment, it is assumed that the camera 2 takes a two-dimensional image and the modeling data generation device 3 generates modeling data. On the other hand, for example, the camera 2 may perform the same operation as the modeling data generation device 3. For example, a program for executing the same operation as the configuration shown in FIG. 3 may be installed in the camera 2 of a smartphone or the like.

The present invention is not limited to the above embodiment, and can be variously modified at the implementation stage without departing from the gist thereof. In addition, each embodiment may be carried out in combination as appropriate, in which case the combined effect can be obtained. Further, the above-described embodiment includes various inventions, and various inventions can be extracted by a combination selected from a plurality of disclosed constituent requirements. For example, even if some constituent elements are deleted from all the constituent elements shown in the embodiment, if the problem can be solved and the effect is obtained, the configuration in which the constituent elements are deleted can be extracted as an invention.

Hereinafter, inventions that can be extracted from the embodiments of the invention of the present application will be described.
[1] A three-dimensional model generation unit that generates a three-dimensional model corresponding to the shoe mark of a two-dimensional image including a shoe mark, and a three-dimensional model generation unit.
A modeling data generation unit that fits polyhedral data to the generated 3D model to generate 3D modeling data for last modeling, and
A modeling data generator equipped with.
[2] A three-dimensional model generation unit that generates a three-dimensional model corresponding to the shoe mark of a two-dimensional image including a shoe mark, and a three-dimensional model generation unit.
A search unit for searching a shoe model, which is a three-dimensional model of shoes having a sole similar to the generated sole of the three-dimensional model, and a search unit.
A modeling data generation unit that fits the searched shoe model to the generated 3D model to generate 3D modeling data for last modeling, and
A modeling data generator equipped with.
[3] The search unit divides the three-dimensional model into a plurality of parts, and searches for the shoe model for each of the divided parts.
The modeling data generation device according to [2].
[4] When the deposit is detected in the shoe mark in the two-dimensional image, the search unit searches the shoe model without using the portion corresponding to the deposit in the three-dimensional model.
The modeling data generation device according to [2] or [3].
[5] The search unit is
Candidates for a plurality of shoe models having a high degree of similarity to the sole of the three-dimensional model are presented to the user.
A shoe model candidate selected by the user among a plurality of shoe model candidates is determined as the shoe model.
The modeling data generation device according to any one of [2]-[4].
[6] When the deposit is detected in the shoe mark in the two-dimensional image, the three-dimensional model generation unit generates the three-dimensional model after removing the portion corresponding to the deposit in the two-dimensional image. Exclude the portion corresponding to the deposit from the three-dimensional model generated or generated.
The modeling data generation device according to any one of [1]-[5].
[7] When the deposit is detected in the shoe mark in the two-dimensional image, the three-dimensional model generation unit determines the deposit based on the image around the portion corresponding to the deposit in the two-dimensional image. The part corresponding to the deposit in the three-dimensional model is generated after complementing the part corresponding to the above, or based on the data around the part corresponding to the deposit in the generated three-dimensional model. Complement,
The modeling data generation device according to any one of [1]-[5].
[8] The modeling data generation device according to any one of [1]-[7], further comprising a control unit for outputting the modeling data to a three-dimensional printer.
[9] Generating a three-dimensional model corresponding to the shoe mark of a two-dimensional image including the shoe mark, and
To generate 3D modeling data for last modeling by fitting polyhedron data to the generated 3D model,
A modeling data generation method.
[10] Generating a three-dimensional model corresponding to the shoe mark of a two-dimensional image including the shoe mark, and
Searching for a shoe model, which is a three-dimensional model of a shoe having a sole similar to the sole of the generated three-dimensional model,
By fitting the searched shoe model to the generated 3D model to generate 3D modeling data for last modeling,
A modeling data generation method.
[11] Generating a three-dimensional model corresponding to the shoe mark of a two-dimensional image including the shoe mark, and
To generate 3D modeling data for last modeling by fitting polyhedron data to the generated 3D model,
A modeling data generation program for making a computer execute.
[12] Generating a three-dimensional model corresponding to the shoe mark of a two-dimensional image including the shoe mark, and
Searching for a shoe model, which is a three-dimensional model of a shoe having a sole similar to the sole of the generated three-dimensional model,
By fitting the searched shoe model to the generated 3D model to generate 3D modeling data for last modeling,
A modeling data generation program for making a computer execute.

1 Modeling data generation system, 2 Cameras, 3 Modeling data generator, 4 3D printer, 31 processor, 32 ROM, 33 RAM, 34 storage, 35 input interface, 36 output interface, 37 communication interface, 38 bus, 311 image acquisition unit 312 3D model generation unit, 313 modeling data generation unit, 314 control unit, 315 search unit.

Claims (12)

A 3D model generation unit that generates a 3D model corresponding to the shoe mark of a 2D image including a shoe mark, and a 3D model generation unit.
A modeling data generation unit that fits polyhedral data to the generated 3D model to generate 3D modeling data for last modeling, and
A modeling data generator equipped with. A 3D model generation unit that generates a 3D model corresponding to the shoe mark of a 2D image including a shoe mark, and a 3D model generation unit.
A search unit for searching a shoe model, which is a three-dimensional model of shoes having a sole similar to the generated sole of the three-dimensional model, and a search unit.
A modeling data generation unit that fits the searched shoe model to the generated 3D model to generate 3D modeling data for last modeling, and
A modeling data generator equipped with. The search unit divides the three-dimensional model into a plurality of parts, and searches for the shoe model for each of the divided parts.
The modeling data generation device according to claim 2. When an deposit is detected in the shoe mark in the two-dimensional image, the search unit searches the shoe model without using the portion corresponding to the deposit in the three-dimensional model.
The modeling data generation device according to claim 2 or 3. The search unit
Candidates for a plurality of shoe models having a high degree of similarity to the sole of the three-dimensional model are presented to the user.
A shoe model candidate selected by the user among a plurality of shoe model candidates is determined as the shoe model.
The modeling data generation device according to any one of claims 2 to 4. When a deposit is detected in the shoe mark in the two-dimensional image, the three-dimensional model generation unit generates or generates the three-dimensional model after removing the portion corresponding to the deposit in the two-dimensional image. Excluding the part corresponding to the deposit from the three-dimensional model.
The modeling data generation device according to any one of claims 1 to 5. When the deposit is detected in the shoe mark in the two-dimensional image, the three-dimensional model generation unit corresponds to the deposit based on the image around the portion corresponding to the deposit in the two-dimensional image. Complement the portion and then generate the 3D model or complement the portion corresponding to the deposit in the 3D model based on the data around the portion corresponding to the deposit in the generated 3D model. ,
The modeling data generation device according to any one of claims 1 to 5. The modeling data generation device according to any one of claims 1 to 7, further comprising a control unit for outputting the modeling data to a three-dimensional printer. To generate a 3D model corresponding to the shoe mark of the 2D image including the shoe mark,
To generate 3D modeling data for last modeling by fitting polyhedron data to the generated 3D model,
A modeling data generation method. To generate a 3D model corresponding to the shoe mark of the 2D image including the shoe mark,
Searching for a shoe model, which is a three-dimensional model of a shoe having a sole similar to the sole of the generated three-dimensional model,
By fitting the searched shoe model to the generated 3D model to generate 3D modeling data for last modeling,
A modeling data generation method. To generate a 3D model corresponding to the shoe mark of the 2D image including the shoe mark,
To generate 3D modeling data for last modeling by fitting polyhedron data to the generated 3D model,
A modeling data generation program for making a computer execute. To generate a 3D model corresponding to the shoe mark of the 2D image including the shoe mark,
Searching for a shoe model, which is a three-dimensional model of a shoe having a sole similar to the sole of the generated three-dimensional model,
By fitting the searched shoe model to the generated 3D model to generate 3D modeling data for last modeling,
A modeling data generation program for making a computer execute.

Images