Image generation system, method, and program

Abstract

To provide an image generation system capable of automatically determining the accuracy required for a three-dimensional image generated in virtual space.SOLUTION: An image generation system includes an image acquisition unit, a generation unit, and an accuracy determination unit. The image acquisition unit captures a two-dimensional image in virtual space that includes an accuracy determination object, which is an object serving as a reference for accuracy determination. The generation unit generates a three-dimensional image including the accuracy determination object from the captured two-dimensional image. The accuracy determination unit determines the accuracy of the generated three-dimensional image depending on whether the accuracy determination object can be recognized.SELECTED DRAWING: Figure 7

Description

[Technical Field]

[0001] The present disclosure relates to an image generation system, an image generation method, and an image generation program that generate three-dimensional (3D) images. [Background technology]

[0002] Visualizing a target object in three dimensions is useful for aiding human understanding. In recent years, technology for reconstructing three-dimensional images from two-dimensional images has been developed.

[0003] For example, Patent Document 1 describes a system for collecting captured images that can be used to generate a three-dimensional model. The system described in Patent Document 1 performs image analysis on captured images showing objects to determine whether or not the captured images show objects that were captured under shooting conditions that are not fully covered by previously collected captured images. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 7414918 Summary of the Invention [Problem to be solved by the invention]

[0005] On the other hand, the accuracy of 3D images is generally judged by users, which places a heavy burden on humans.

[0006] Therefore, an object of the present disclosure is to provide an image generation system, an image generation method, and an image generation program that can automatically determine the accuracy required for a three-dimensional image generated in a virtual space. [Means for solving the problem]

[0007] The image generation system according to the present disclosure is characterized by comprising an image acquisition unit that captures a two-dimensional image in a virtual space that includes an accuracy determination object, which is an object that is used as the basis for accuracy determination; a generation unit that generates a three-dimensional image that includes the accuracy determination object from the captured two-dimensional image; and an accuracy determination unit that determines the accuracy of the generated three-dimensional image depending on whether the accuracy determination object can be recognized.

[0008] The image generation method according to the present disclosure is characterized in that a 2D image is captured in a virtual space that includes an accuracy judgment object, which is an object that is used as the basis for accuracy judgment, a 3D image that includes the accuracy judgment object is generated from the captured 2D image, and the accuracy of the generated 3D image is determined depending on whether the accuracy judgment object can be recognized.

[0009] The image generation program according to the present disclosure is characterized in that it causes a computer to execute an image acquisition process for capturing a two-dimensional image in a virtual space that includes an accuracy determination object, which is an object that is used as the basis for accuracy determination; a generation process for generating a three-dimensional image that includes the accuracy determination object from the captured two-dimensional image; and an accuracy determination process for determining the accuracy of the generated three-dimensional image depending on whether the accuracy determination object can be recognized. [Effects of the Invention]

[0010] According to the present disclosure, it is possible to automatically determine the accuracy required for a three-dimensional image generated in a virtual space. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is an explanatory diagram illustrating a configuration example of an embodiment of a video generation system according to the present disclosure. [Figure 2] FIG. 10 is an explanatory diagram showing an example of a process for constructing a virtual space in which an accuracy determination object is embedded. [Figure 3] 10 is a flowchart illustrating an example of the operation of the video generation system. [Figure 4] FIG. 10 is an explanatory diagram illustrating a configuration example of another embodiment of an image generation system according to the present disclosure. [Figure 5] 10 is a flowchart illustrating another example of the operation of the video generation system. [Figure 6] FIG. 10 is an explanatory diagram illustrating a configuration example of still another embodiment of an image generation system according to the present disclosure. [Figure 7] 1 is a block diagram showing an overview of an image generation system according to the present disclosure. [Figure 8] FIG. 1 is a schematic block diagram illustrating the configuration of a computer according to at least one embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0013] Embodiment 1. In the first embodiment, an image generation system that automatically determines the accuracy required for a 3D image generated in a virtual space will be described. FIG. 1 is an explanatory diagram showing a configuration example of the first embodiment of the image generation system of the present disclosure. The image generation system 100 of this embodiment includes a storage unit 10, a virtual space construction unit 20, an image acquisition unit 30, a generation unit 40, and an accuracy determination unit 50.

[0014] The storage unit 10 stores various types of information used for processing by the video generation system 100. The storage unit 10 may store, for example, various types of information used by a virtual space construction unit 20 (described later) to generate a virtual space, a model representing the virtual space, a 3D (three dimensions) animation representing the virtual space, and the like.

[0015] Note that models representing virtual spaces and aspects of 3D animation representing virtual spaces are widely known, and therefore detailed explanations will be omitted here. The storage unit 10 is realized by, for example, a magnetic disk.

[0016] The virtual space construction unit 20 constructs a virtual space to be used for generating a three-dimensional image. In this embodiment, the virtual space construction unit 20 receives input of an accuracy judgment object (hereinafter, also referred to as a marker), which is an object that is used as a criterion for accuracy judgment by the accuracy judgment unit 50 (described later), and constructs a virtual space including the accuracy judgment object.

[0017] For example, if a precision that allows a predetermined size to be determined is required, the virtual space construction unit 20 may generate a virtual space in which a precision determination object that represents that size is embedded.

[0018] Fig. 2 is an explanatory diagram showing an example of the process of constructing a virtual space in which an accuracy judgment object is embedded. In the example shown in Fig. 2, it is assumed that the accuracy required is such that a size of 2m x 2m can be determined in a 3D image. Fig. 2 shows that a virtual space construction unit 20 receives from a user an instruction to set an accuracy judgment object 11, which displays the letter (A) in a rectangular area representing that size, and generates a 3D image 12 in which the received accuracy judgment object is embedded in the wall of a building.

[0019] Furthermore, for example, if the 3D image requires accuracy that allows a predetermined situation to be determined, the virtual space construction unit 20 may generate a virtual space in which an accuracy determination object that reproduces the situation is embedded. Examples of predetermined situations include a situation in which two men are fighting in the street, or a situation in which a user wants to find a cat. In this case, the generation unit 40 may generate an object that reproduces the situation and embed it in the 3D image.

[0020] The method by which the virtual space construction unit 20 constructs the virtual space is arbitrary, and any known method may be used. For example, the virtual space construction unit 20 may construct a 3D animation, which is the virtual space, from a model stored in the storage unit 10, or may output the 3D animation stored in the storage unit 10 itself.

[0021] Generally, in a three-dimensional CG (Computer Graphics) world, it is possible to set objects that correspond to real-world units (e.g., cm, etc.). Therefore, the virtual space construction unit 20 may embed a three-dimensional accuracy determination object (three-dimensional) for determining a desired accuracy in, for example, the base three-dimensional CG data (i.e., the computer graphics world having three-dimensional coordinate information).

[0022] The image acquisition unit 30 captures a video or a plurality of still images (hereinafter simply referred to as 2D images) in the virtual space constructed by the virtual space construction unit 20. Specifically, the image acquisition unit 30 of this embodiment captures 2D images in the virtual space that include at least the accuracy determination object. Note that as long as an image that includes the accuracy determination object in its range is captured, the position and angle at which the 2D image is captured and the parameters set during capture (for example, parameters indicating the camera's viewing angle, focus, aperture, etc.) are arbitrary.

[0023] The method for capturing two-dimensional images in the virtual space may also be arbitrary. For example, the image capture unit 30 may place a virtual agent of the assumed user in the virtual space and capture two-dimensional images for each location that can be viewed through the virtual agent.

[0024] Furthermore, the image acquisition unit 30 may acquire, together with capturing an image, information indicating the location where the image was captured and the surrounding conditions of that location.

[0025] The generation unit 40 generates a 3D image from the captured 2D image. In this embodiment, since the image acquisition unit 30 captures a 2D image that includes the accuracy judgment object within its range, the generation unit 40 generates a 3D image in which the accuracy judgment object is embedded. Note that the method by which the generation unit 40 generates a 3D image from a 2D image is arbitrary.

[0026] The accuracy determination unit 50 determines the accuracy of the generated 3D video. Specifically, the accuracy determination unit 50 determines the accuracy of the generated 3D video depending on whether an accuracy determination object embedded in the 3D video is recognizable.

[0027] The method for recognizing the accuracy judgment object is determined in advance depending on the aspect of the accuracy judgment object. For example, if a character of a predetermined size is embedded as the accuracy judgment object, the accuracy judgment unit 50 may use a known character recognition method to determine whether the accuracy judgment object indicated by that size can be recognized. Also, for example, if an accuracy judgment object that reproduces a predetermined situation is embedded as the accuracy judgment object, the accuracy judgment unit 50 may use a known image recognition method to determine whether the accuracy judgment object indicating that situation can be recognized.

[0028] The accuracy determining unit 50 may determine that the required accuracy is met when the rate at which recognition is possible (recognition success rate) reaches a predetermined standard (for example, 100%, 90% or more, etc.).

[0029] The virtual space construction unit 20, the image acquisition unit 30, the generation unit 40, and the accuracy determination unit 50 are realized by a computer processor (e.g., a CPU (Central Processing Unit), a GPU (Graphics Processing Unit)) that operates according to a program (image generation program). For example, the program may be stored in the storage unit 10 of the image generation system 100, and the processor may read the program and operate as the virtual space construction unit 20, the image acquisition unit 30, the generation unit 40, and the accuracy determination unit 50 according to the program.

[0030] Furthermore, each function of the image generation system 100 may be provided in the form of SaaS (Software as a Service). Furthermore, the virtual space construction unit 20, the image acquisition unit 30, the generation unit 40, and the accuracy determination unit 50 may each be realized by dedicated hardware.

[0031] Furthermore, some or all of the components of each device may be realized by general-purpose or dedicated circuits, processors, etc., or a combination of these. These may be configured by a single chip, or by multiple chips connected via a bus. Some or all of the components of each device may be realized by a combination of the above-mentioned circuits, etc., and programs.

[0032] Furthermore, when some or all of the components of the video generation system 100 are realized by a plurality of information processing devices, circuits, etc., the plurality of information processing devices, circuits, etc. may be centrally or decentralized. For example, the information processing devices, circuits, etc. may be realized as a client-server system, a cloud computing system, or the like, in a form in which each is connected via a communication network.

[0033] Next, an example of the operation of the video generation system 100 of this embodiment will be described. Fig. 3 is a flowchart showing an example of the operation of the video generation system 100 of this embodiment. The video acquisition unit 30 captures a 2D video that includes an accuracy judgment object in its range in a virtual space (step S11). The generation unit 40 generates a 3D video that includes the accuracy judgment object from the captured 2D video (step S12). Then, the accuracy judgment unit 50 judges the accuracy of the generated 3D video depending on whether the accuracy judgment object can be recognized (step S13).

[0034] As described above, in this embodiment, the image acquisition unit 30 captures a 2D image in a virtual space that includes an accuracy determination object, and the generation unit 40 generates a 3D image that includes the accuracy determination object from the captured 2D image. The accuracy determination unit 50 then determines the accuracy of the generated 3D image depending on whether the accuracy determination object can be recognized. Therefore, it is possible to automatically determine whether the 3D image generated in the virtual space meets the required accuracy.

[0035] Embodiment 2. Next, a second embodiment of the image generation system of the present disclosure will be described. In the second embodiment, an image generation system that autonomously improves the accuracy of a 3D image of an object to be imaged in a virtual space will be described.

[0036] 4 is an explanatory diagram showing a configuration example of a second embodiment of the image generation system of the present disclosure. The image generation system 200 of this embodiment includes a storage unit 110, a virtual space construction unit 120, a determination unit 130, an image acquisition unit 140, a generation unit 150, and an evaluation unit 160.

[0037] The storage unit 110 stores various types of information used for processing by the video generation system 200. The storage unit 110 may store, for example, various types of information used by the virtual space construction unit 120 (described later) to construct a virtual space, a model representing the virtual space, a 3D animation representing the virtual space, and the like.

[0038] As in the first embodiment, models representing virtual spaces and aspects of 3D animation representing virtual spaces are widely known, and therefore detailed description thereof will be omitted here. The storage unit 110 is realized by, for example, a magnetic disk.

[0039] The virtual space construction unit 120 constructs a virtual space to be used for generating three-dimensional images, similar to the virtual space construction unit 20 of the first embodiment.

[0040] The determination unit 130 determines a plurality of imaging positions in the virtual space and an imaging method at each imaging position. In this embodiment, the imaging method determined by the determination unit 130 is to determine changeable parameters (angle, field of view, focus, aperture, etc.) that are set in a camera or the like when capturing an image. Initial values ​​of the imaging positions and parameters are set arbitrarily. Note that a method for changing the imaging positions and parameters will be described later.

[0041] The image acquisition unit 140 captures a two-dimensional image in the virtual space at the determined imaging position according to the determined imaging method (parameters). When the accuracy determination object shown in the first embodiment is used, the image acquisition unit 30 may capture a two-dimensional image in the virtual space that includes the accuracy determination object in its range. The method for capturing a two-dimensional image in the virtual space is arbitrary.

[0042] The generation unit 150 generates a 3D image from the captured 2D image. Note that any method may be used to generate a 3D image from a 2D image, and any known method may be used. Furthermore, when the accuracy judgment object shown in the first embodiment is used, the generation unit 150 may generate a 3D image in which the accuracy judgment object is embedded.

[0043] The evaluation unit 160 evaluates the generated 3D video based on a predetermined viewpoint. The evaluation viewpoint may be the viewpoint of the accuracy of the 3D video generated based on a plurality of 2D videos, the viewpoint of the imaging efficiency of the plurality of 2D videos, or a combination of these viewpoints. The evaluation unit 160 may evaluate the generated 3D video based on an objective function that calculates an evaluation value based on these viewpoints.

[0044] For example, when performing evaluation from the viewpoint of accuracy, the evaluation unit 160 may evaluate the 3D video using an objective function based on a known image recognition method, in which the higher the recognition rate of the object to be imaged, the higher the evaluation. Note that, when the accuracy determination object in the first embodiment is used, the evaluation unit 160 may determine the accuracy of the generated 3D video depending on whether the accuracy determination object is recognizable, and use the determined accuracy as the evaluation result.

[0045] Furthermore, when evaluating from the viewpoint of the efficiency of capturing 2D images, the evaluation unit 160 may evaluate the 3D images using an objective function that increases the evaluation the shorter the distance between the image capturing positions and the smaller the change in parameters when capturing the 2D images. According to these evaluations, it can be said that a shooting order (shooting route) with a shorter distance is preferable, and that the smaller the change in camera angle before and after shooting is, the more preferable it is.

[0046] If the evaluation by the evaluation unit 160 does not satisfy a predetermined standard, the determination unit 130 optimizes the imaging positions and imaging method so that the evaluation by the evaluation unit 160 is higher. Note that any optimization method may be used. For example, once the object to be photographed is determined, imaging positions surrounding the object are determined. The imaging route is determined by selecting and connecting multiple imaging positions from among these multiple imaging positions. When imaging is assumed to be performed using a drone in the real world, it is possible to create an optimization problem with factors (parameters) such as the travel distance, travel speed (photography time), and changes in the imaging angle.

[0047] As an example, the determination unit 130 may determine an imaging position and an imaging method for capturing a two-dimensional image so as to minimize changes in the imaging method (i.e., parameters) and shorten the moving distance (moving path) of the imaging position when capturing an image of an object to be captured. Then, the image acquisition unit 140 captures a two-dimensional image according to the optimized imaging position and imaging method.

[0048] Virtual space construction unit 120, determination unit 130, image acquisition unit 140, generation unit 150, and evaluation unit 160 are realized by a computer processor that operates according to a program (image generation program). For example, the program may be stored in storage unit 110 of image generation system 200, and the processor may read the program and operate as virtual space construction unit 120, determination unit 130, image acquisition unit 140, generation unit 150, and evaluation unit 160 according to the program.

[0049] Next, a description will be given of an example of the operation of the image generation system 200 of this embodiment. Fig. 5 is a flowchart showing an example of the operation of the image generation system 200 of this embodiment. In this example of operation, it is assumed that the initial states of the imaging position and imaging method are determined in advance.

[0050] The image acquisition unit 140 captures a 2D image in the virtual space at the determined imaging position according to the imaging method (step S21). The generation unit 150 generates a 3D image from the captured 2D image (step S22). The evaluation unit 160 evaluates the generated 3D image (step S23). If the evaluation satisfies a predetermined standard (Yes in step S24), the process ends.

[0051] On the other hand, if the evaluation does not satisfy the predetermined standard (No in step S24), the determination unit 130 optimizes the imaging position and imaging method so as to increase the evaluation (step S25). Then, the image acquisition unit 140 captures a 2D image in accordance with the optimized imaging position and imaging method (step S26). Thereafter, the processes from step S22 onwards are repeated.

[0052] As described above, in this embodiment, the determination unit 130 determines multiple imaging positions in the virtual space and imaging methods at each imaging position, and the image acquisition unit 140 captures 2D images in the virtual space at the determined imaging positions according to the imaging methods. The generation unit 150 then generates 3D images from the captured 2D images, and the evaluation unit 160 evaluates the generated 3D images. Here, the determination unit 130 optimizes the imaging positions and imaging methods to increase the evaluation, and the image acquisition unit 140 captures 2D images according to the optimized imaging positions and imaging methods. This makes it possible to autonomously improve the accuracy of 3D images of objects to be captured in the virtual space.

[0053] Then, in the real world, by controlling a drone or the like according to the imaging position and imaging method determined in this way, it becomes possible to obtain 2D images in a more favorable environment.

[0054] Embodiment 3. Next, a third embodiment of the image generation system of the present disclosure will be described. The third embodiment is a combination of the image generation system of the first embodiment and the image generation system of the second embodiment.

[0055] 6 is an explanatory diagram showing a configuration example of a third embodiment of an image generation system according to the present disclosure. The image generation system 300 of this embodiment includes a storage unit 210, a virtual space construction unit 220, a determination unit 230, an image acquisition unit 240, a generation unit 250, an accuracy determination unit 260, and an evaluation unit 270.

[0056] The storage unit 210 stores both the information stored in the storage unit 10 in the first embodiment and the information stored in the storage unit 110 in the second embodiment. The storage unit 210 is realized by, for example, a magnetic disk.

[0057] The virtual space construction unit 220 constructs a virtual space to be used for generating three-dimensional video images, similar to the virtual space construction unit 20 in the first embodiment and the virtual space construction unit 120 in the second embodiment.

[0058] The determination unit 230 determines a plurality of imaging positions in the virtual space and an imaging method at each imaging position, similar to the determination unit 130 in the second embodiment. Specifically, the determination unit 230 optimizes the imaging positions and the imaging method so as to increase the evaluation by the evaluation unit 270, which will be described later.

[0059] The image acquisition unit 240 captures a two-dimensional image including the accuracy assessment object in its range at the determined or optimized imaging position and in accordance with the determined or optimized imaging method (parameters).

[0060] The generating unit 150 generates a three-dimensional video including an accuracy assessment object from a captured two-dimensional video, similar to the generating unit 40 in the first embodiment.

[0061] The accuracy determination unit 260, like the accuracy determination unit 50 in the first embodiment, determines the accuracy of the generated three-dimensional video image depending on whether the accuracy determination object is recognizable.

[0062] The evaluation unit 270 evaluates at least the accuracy determination result by the accuracy determination unit 260 .

[0063] Virtual space construction unit 220, determination unit 230, image acquisition unit 240, generation unit 250, accuracy determination unit 260, and evaluation unit 270 are realized by a computer processor that operates according to a program (image generation program).

[0064] With the above configuration, it is possible to obtain the respective effects of the first and second embodiments.

[0065] Next, an overview of the present disclosure will be described. Fig. 7 is a block diagram showing an overview of an image generation system of the present disclosure. An image generation system 80 (e.g., image generation system 100) according to the present disclosure includes an image acquisition unit 81 (e.g., image acquisition unit 30) that captures a two-dimensional image in a virtual space that includes an accuracy determination object, which is an object that serves as a reference for accuracy determination, a generation unit 82 (e.g., generation unit 40) that generates a three-dimensional image that includes the accuracy determination object from the captured two-dimensional image, and an accuracy determination unit 83 (e.g., accuracy determination unit 50) that determines the accuracy of the generated three-dimensional image depending on whether the accuracy determination object can be recognized.

[0066] Such a configuration makes it possible to automatically determine the accuracy required for 3D images generated in virtual space.

[0067] Furthermore, the image generation system 80 may include a virtual space construction unit (e.g., virtual space construction unit 20) that generates a virtual space in which an accuracy determination object representing a predetermined size (e.g., a character of 2m x 2m size) is embedded. Then, the image acquisition unit 81 may capture a two-dimensional image in the virtual space that includes the accuracy determination object within its range, and the accuracy determination unit 83 may determine whether or not the accuracy determination object indicated by its size can be recognized.

[0068] Furthermore, the image generation system 80 may include a virtual space construction unit (e.g., virtual space construction unit 20) that generates a virtual space in which an accuracy determination object representing a predetermined situation (e.g., a fighting situation, a situation in which a cat is found) is embedded. Then, the image acquisition unit 81 may capture a two-dimensional image in the virtual space that includes the accuracy determination object within its range, and the accuracy determination unit 83 may determine whether or not the accuracy determination object representing that situation can be recognized.

[0069] The accuracy determination object may be determined in advance by the user in accordance with the accuracy required for the three-dimensional image and set in the virtual space.

[0070] Furthermore, the video generation system 80 may include a determination unit (e.g., determination unit 230) that determines a plurality of imaging positions in the virtual space and an imaging method (e.g., parameters) at each of the imaging positions, and an evaluation unit (e.g., evaluation unit 270) that evaluates the accuracy determination result by the accuracy determination unit 83. The determination unit may then optimize the imaging positions and imaging methods to increase the evaluation, and the video acquisition unit 81 may capture a two-dimensional video in the virtual space at the determined imaging positions in accordance with the imaging method.

[0071] Specifically, the determination unit may determine the imaging position and imaging method for capturing the two-dimensional image by optimizing the imaging method so that there is little change in the imaging method and the distance the imaging position needs to move when capturing an object to be captured is short.

[0072] 8 is a schematic block diagram showing the configuration of a computer according to at least one embodiment. The computer 1000 includes a processor 1001, a main memory device 1002, an auxiliary memory device 1003, and an interface 1004. The computer 1000 may also be connected to a computer that executes a mathematical programming solver, an annealing machine, a simulator, or the like.

[0073] The above-described image generation system 80 is implemented in a computer 1000. The operations of the above-described processing units are stored in the form of a program (image generation program) in an auxiliary storage device 1003. The processor 1001 reads the program from the auxiliary storage device 1003, loads it into the main storage device 1002, and executes the above-described processing in accordance with the program.

[0074] In at least one embodiment, the auxiliary storage device 1003 is an example of a non-transitory tangible medium. Other examples of non-transitory tangible media include a magnetic disk, a magneto-optical disk, a CD-ROM (Compact Disc Read-only memory), a DVD-ROM (Read-only memory), and a semiconductor memory connected via the interface 1004. In addition, when this program is distributed to the computer 1000 via a communication line, the computer 1000 that receives the program may load the program into the main storage device 1002 and execute the above processing.

[0075] The program may also be a program for realizing part of the above-described functions. Furthermore, the program may be a so-called differential file (differential program) that realizes the above-described functions in combination with another program already stored in the auxiliary storage device 1003.

[0076] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0077] (Supplementary Note 1) An image acquisition unit that captures a two-dimensional image in a virtual space that includes an accuracy judgment object, which is an object that is used as a standard for accuracy judgment; a generating unit that generates a three-dimensional image including the accuracy assessment object from the captured two-dimensional image; an accuracy determination unit that determines the accuracy of the generated three-dimensional image depending on whether the accuracy determination object can be recognized; A video generation system characterized by:

[0078] (Appendix 2) A virtual space construction unit that generates a virtual space in which an accuracy determination object representing a predetermined size is embedded, the image acquisition unit captures a two-dimensional image in the virtual space that includes the accuracy determination object within its range; The accuracy determination unit determines whether or not the accuracy determination object indicated by the size can be recognized. 10. The video generation system of claim 1.

[0079] (Appendix 3) A virtual space construction unit that generates a virtual space in which an accuracy determination object representing a predetermined situation is embedded, the image acquisition unit captures a two-dimensional image in the virtual space that includes the accuracy determination object within its range; The accuracy determination unit determines whether or not the accuracy determination object indicating the situation can be recognized. 10. The video generation system of claim 1.

[0080] (Note 4) The accuracy determination object is set in the virtual space in advance by the user according to the accuracy required for the 3D image. 4. The image generation system according to claim 1, wherein the image generation system comprises:

[0081] (Supplementary Note 5) A determination unit that determines a plurality of imaging positions in the virtual space and an imaging method at each of the imaging positions; an evaluation unit that evaluates the accuracy determination result by the accuracy determination unit, the determination unit optimizes the imaging position and the imaging method so as to increase the evaluation; The image acquisition unit captures a two-dimensional image in the virtual space at the determined imaging position according to the imaging method. 5. The image generation system according to any one of claims 1 to 4.

[0082] (Supplementary Note 6) The determination unit determines the imaging position and imaging method for capturing the two-dimensional video by optimizing the imaging method so that changes in the imaging method are minimal and the moving distance of the imaging position when capturing an image of an object to be captured is short. 6. The video generation system of claim 5.

[0083] (Appendix 7) In the virtual space, a 2D image is captured that includes an accuracy judgment object, which is an object that is used as a standard for accuracy judgment, within the range of the image. generating a three-dimensional image including the accuracy determination object from the captured two-dimensional image; The accuracy of the generated three-dimensional image is determined depending on whether the accuracy determination object can be recognized. A video generation method comprising:

[0084] (Appendix 8) A virtual space is generated in which an accuracy judgment object representing a predetermined size is embedded, capturing a two-dimensional image including the accuracy determination object in the virtual space; The accuracy determination object indicated by the size is determined to be recognizable or not. 8. The image generation method of claim 7.

[0085] (Appendix 9) A virtual space is generated in which an accuracy judgment object representing a predetermined situation is embedded, capturing a two-dimensional image including the accuracy determination object in the virtual space; Determine whether or not the accuracy determination object indicating the situation can be recognized. 8. The image generation method of claim 7.

[0086] (Appendix 10) To the computer, an image acquisition process for capturing a two-dimensional image in a virtual space that includes an accuracy determination object, which is an object that is used as a reference for accuracy determination; A generation process for generating a three-dimensional image including the accuracy determination object from the captured two-dimensional image; and An accuracy determination process for determining the accuracy of the generated three-dimensional image depending on whether the accuracy determination object can be recognized. An image generation program for executing the above.

[0087] (Appendix 11) To the computer, Executing a virtual space construction process to generate a virtual space in which an accuracy determination object representing a predetermined size is embedded; In an image acquisition process, a two-dimensional image including the accuracy determination object in a range is captured in the virtual space; In the accuracy determination process, it is determined whether or not the accuracy determination object indicated by the size can be recognized. 11. The video generation program according to claim 10.

[0088] (Appendix 12) To the computer, Executing a virtual space construction process to generate a virtual space in which an accuracy determination object representing a predetermined situation is embedded; In an image acquisition process, a two-dimensional image including the accuracy determination object in a range is captured in the virtual space; In the accuracy determination process, the accuracy determination object indicating the situation is determined to be recognizable or not. 11. The video generation program according to claim 10.

[0089] Although the present invention has been described above with reference to the embodiments and examples, the present invention is not limited to the above-described embodiments and examples. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. [Explanation of symbols]

[0090] 10,110,210 Storage section 20,120,220 Virtual Space Construction Department 30,140,240 Video acquisition unit 40,150,250 generation part 50,260 Accuracy judgment section 100,200,300 Video Creation System 130,230 Decision Section 160,270 Evaluation Department

Claims

1. an image acquisition unit that captures a two-dimensional image in a virtual space that includes an accuracy determination object that is an object used as a reference for accuracy determination; a generating unit that generates a three-dimensional image including the accuracy determination object from the captured two-dimensional image; an accuracy determination unit that determines the accuracy of the generated three-dimensional image depending on whether the accuracy determination object can be recognized; A video generation system characterized by:

2. a virtual space construction unit that generates a virtual space in which an accuracy determination object representing a predetermined size is embedded; the image acquisition unit captures a two-dimensional image in the virtual space that includes the accuracy determination object; The accuracy determination unit determines whether or not the accuracy determination object indicated by the size can be recognized. The video production system of claim 1 .

3. a virtual space construction unit that generates a virtual space in which an accuracy determination object representing a predetermined situation is embedded; the image acquisition unit captures a two-dimensional image in the virtual space that includes the accuracy determination object; The accuracy determination unit determines whether or not the accuracy determination object indicating the situation can be recognized. The video production system of claim 1 .

4. The accuracy determination object is set in the virtual space in advance by the user according to the accuracy required for the three-dimensional image. The image generation system according to any one of claims 1 to 3.

5. a determination unit that determines a plurality of imaging positions in the virtual space and an imaging method at each of the imaging positions; an evaluation unit that evaluates the accuracy determination result by the accuracy determination unit, the determination unit optimizes the imaging position and the imaging method so as to increase the evaluation; The image acquisition unit captures a two-dimensional image in the virtual space at the determined imaging position according to the imaging method. The image generation system according to any one of claims 1 to 3.

6. The determination unit determines the imaging position and imaging method for capturing the two-dimensional video by optimizing the imaging method so that changes in the imaging method are minimal and the moving distance of the imaging position when capturing an image of the object to be captured is short. The video generation system according to claim 5.

7. capturing a two-dimensional image in a virtual space that includes an accuracy determination object, which is an object that is used as a reference for accuracy determination; generating a three-dimensional image including the accuracy determination object from the captured two-dimensional image; The accuracy of the generated three-dimensional image is determined depending on whether the accuracy determination object can be recognized. A video generation method comprising:

8. generating a virtual space in which an accuracy determination object representing a predetermined size is embedded; capturing a two-dimensional image including the accuracy determination object in the virtual space; The accuracy determination object indicated by the size is determined to be recognizable or not. The image generating method according to claim 7.

9. generating a virtual space in which an accuracy determination object representing a predetermined situation is embedded; capturing a two-dimensional image including the accuracy determination object in the virtual space; Determine whether or not the accuracy determination object indicating the situation can be recognized. The image generating method according to claim 7.

10. On the computer, an image acquisition process for capturing a two-dimensional image in a virtual space that includes an accuracy determination object, which is an object that is used as a reference for accuracy determination; A generation process for generating a three-dimensional image including the accuracy determination object from the captured two-dimensional image; and an accuracy determination process for determining the accuracy of the generated three-dimensional image depending on whether the accuracy determination object can be recognized; An image generation program for executing the above.

Images