JP4366709B2 - Image processing method, simulation apparatus, program, and recording medium - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a method for supporting vehicle planning.
[0002]
[Prior art]
Conventionally, when evaluating the visibility of a planned vehicle from the inside of a vehicle, a prototype vehicle and a clay model in the shape of an interior have been created.
[0003]
[Problems to be solved by the invention]
Therefore, in the conventional planning work, a great deal of labor is spent on creating a prototype vehicle and a clay model, which has a problem that it takes a lot of time and cost.
[0004]
On the other hand, attempts are being made to generate computer graphics images that virtually represent the planned vehicle and perform visibility evaluation using the computer graphics images. However, if a landscape image that can be seen by the driver of the planned vehicle is represented by a computer graphics image, there is a problem that the reality is too thin and accurate evaluation of visibility is difficult.
[0005]
In addition, when a landscape image that can be seen by the driver of the planned vehicle is expressed as a computer graphics image, it takes a very long time and a great amount of time to generate the computer graphics image. For this reason, various landscape images cannot be easily generated, and only uniform visibility evaluation can be performed. Further, the computer processing becomes excessive when reproducing.
[0006]
The present invention has been made to solve such problems of the prior art, and an object of the present invention is to quickly and easily generate an image suitable for evaluating the visibility of a planned vehicle. An image processing method that can be performed, a simulation device that evaluates the visibility of a planned vehicle using such an image, a program, and a recording medium.
[0007]
[Means for Solving the Problems]
  In order to achieve the above object, the method according to the present invention comprises:
  An image processing method for generating an image for evaluating visibility during driving in a planned vehicle,
  A shooting process of shooting a surrounding image of an existing vehicle in which the shooting means is running;
  An input step for inputting an area that is estimated to be seen by a driver in order to identify an area to be cut out from a peripheral image photographed in the photographing step;
  An extraction unit extracts a partial image from a peripheral image photographed in the photographing step based on the region input in the input step, and generates a background image for visibility evaluation;
  A display step for generating and displaying a visibility evaluation image by superimposing the background image generated in the extraction step and a computer graphics image representing the interior of the planned vehicle;
  HaveAnd
  The input step includes
  Photographing the driver's line-of-sight direction with a camera attached to the driver's head;
  Or
  Photographing the driver's head with a camera and detecting the driver's field of view from the movement of the driver's head;
  includingIt is characterized by that.
[0009]
  The shooting process was attached to the external surface of the existing vehicleFor peripheral shootingSaid by cameraExistingA step of taking a surrounding image of the vehicle,ExtractionThe process includes the peripheral image captured in the imaging process,For peripheral shootingThe method includes a step of correcting according to a difference in position between the camera and the driver's viewpoint..
[0010]
  In order to achieve the above object, an apparatus according to the present invention is a simulation apparatus for evaluating visibility during driving in a planned vehicle, and is attached to an existing vehicle.For peripheral shootingA first input means for inputting a peripheral image photographed by a camera;FirstIn order to identify the area to be cut out from the peripheral image input by the input means, the second input means for inputting the area estimated to be seen by the driver on board, and the peripheral image input by the first input means Extracting a partial image of the field of view input by the second input means and generating a background image for visibility evaluation; the background image generated by the extraction means; and an interior of the planned vehicle. Display means for generating and displaying an image for visibility evaluation by superimposing a computer graphics image to be represented, and the second input means is configured by the camera attached to the driver's head. Means for photographing the driver's line-of-sight direction, or means for photographing the driver's head with a camera and detecting the driver's field of view from the movement of the driver's head. To.
[0011]
  Furthermore, theFirstThe surrounding image input by the input means isFor peripheral shootingIt has a means to correct | amend according to the difference in the position of a camera and the said driver | operator's viewpoint.
[0012]
  In order to achieve the above object, a program according to the present invention is a program for causing a computer to function as a simulation device for evaluating visibility during driving in a planned vehicle, and is attached to an existing vehicle in the computer. A first input means for inputting a running peripheral image photographed by a camera;FirstA second input means for inputting an area that is estimated to be seen by a driver on board to identify an area to be cut out from the peripheral image input by the input means;FirstExtracting means for extracting a partial image of the view area input by the second input means from the peripheral image input by the input means and generating a background image for visibility evaluation; and the background image generated by the extracting means And a display means for generating and displaying an image for visibility evaluation by superimposing a computer graphics image representing the interior of the planned vehicle, wherein the second input The means is means for photographing the driver's line-of-sight direction with a camera attached to the driver's head, or the driver's head is photographed by the camera, and the driving is performed based on the movement of the driver's head. Means for detecting a person's field of view.
[0013]
In order to achieve the above object, a storage medium according to the present invention stores the above program.
[0014]
【The invention's effect】
According to the present invention, a landscape estimated to be seen from the driver of a planned vehicle can be represented by a live-action image. Thereby, the visibility of the planning vehicle can be more accurately evaluated. It is possible to easily generate a landscape image when it is assumed that the planned vehicle is driven in various driving environments.
[0015]
In addition, a real-life landscape image and a computer graphics image representing the interior of the planned vehicle are superimposed on each other to generate a visibility evaluation image. Compared with the case of creating, the time and cost required for vehicle planning can be greatly reduced.
[0016]
Also, if a partial image of the driver's field of view is extracted from the image taken by the camera attached to the external surface of the existing vehicle, and the partial image is corrected according to the difference between the camera position and the driver's viewpoint position, A more accurate image for visibility evaluation can be obtained. Thereby, visibility can be evaluated with high accuracy.
[0017]
Further, if the image is taken with a camera attached to the driver's head, the driver's field of view can be determined easily and accurately, and a more accurate visibility evaluation image can be obtained. Thereby, visibility can be evaluated with high accuracy.
[0018]
Further, if the movement of the driver's head is photographed with a camera, a change in the driver's field of view during driving can be accurately detected, and a more accurate visibility evaluation image can be obtained. Thereby, visibility can be evaluated with high accuracy.
[0019]
Further, according to the apparatus, program, and storage medium according to the present invention, a partial image of a driver's field of view riding in an existing vehicle is extracted from a peripheral image taken by a camera attached to the existing vehicle, By superimposing the extracted partial image and a computer graphics image representing the interior of the planned vehicle, it is possible to generate and display an image for visibility evaluation estimated to be visible to the driver in the planned vehicle. . As a result, the visibility of the planned vehicle can be more accurately evaluated, and a landscape image can be easily generated when it is assumed that the planned vehicle has traveled in various travel environments. Furthermore, the time and cost required for vehicle planning can be greatly reduced as compared with the case of creating a prototype vehicle or an interior clay model.
[0020]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
The embodiment described below is an example as means for realizing the present invention, and the present invention can be applied to a modified or modified embodiment described below without departing from the spirit of the present invention.
[0021]
(First embodiment)
First, as a first embodiment of the present invention, an image processing method for generating an image for evaluating visibility during driving in a planned vehicle will be described.
[0022]
<Camera equipment>
FIG. 1 is a diagram showing a photographing vehicle that acquires an image for visibility evaluation. In FIG. 1, reference numeral 101 denotes a photographing vehicle, and an existing vehicle that is generally available on the market can be used. A first camera 102 and a second camera 103 are attached to the photographing vehicle 101. The first camera 102 and the second camera 103 are each a video camera. As shown in the figure, the first camera 102 is attached to the outer surface (for example, on the hood) of the photographing vehicle 101, and the second camera 103 is attached to the driver's seat portion of the photographing vehicle 101. It is preferable that the second camera 103 is attached to the head of the driver who actually drives the photographing vehicle, and images the driver's line of sight. By doing so, the driver's field of view can be obtained easily and accurately, a more accurate visibility evaluation image can be obtained, and the visibility can be evaluated with high accuracy.
[0023]
Then, by driving the first camera 102 while driving the photographing vehicle 101, a peripheral image of the photographing vehicle 101 is photographed, and at the same time, the second camera 103 is driven to get on the photographing vehicle 101. To obtain the driver's field of view.
[0024]
Specifically, the first camera 102 performs wide-angle shooting, and acquires a wide range of images that can be seen by the driver who is in the shooting vehicle 101 during normal driving. The second camera 103 captures an image with the same angle of view as the human field of view, and the captured image is used to specify an area to be cut out from the captured image of the first camera 102. A plurality of cameras may be provided as the first camera that captures a surrounding image of the vehicle.
[0025]
<Image processing system>
Next, a system for generating an image for visibility evaluation from an image photographed by the first camera 102 and an image photographed by the second camera 103 will be described.
[0026]
FIG. 2 is a block diagram illustrating a system for generating an image for visibility evaluation. This system is configured by installing an operation system and predetermined image processing software on a general-purpose personal computer system 1.
[0027]
In FIG. 2, the computer system 1 includes a CPU 11, a ROM (Read Only Memory) 13, a RAM (Random Access Memory) 14, an external storage unit 15, an input unit 16, a display unit 17, and an image processing unit 18. Are connected by a system bus 12.
[0028]
Among these, the CPU 11 executes various arithmetic processes by executing programs stored in the ROM 13 and the RAM 14.
[0029]
The ROM 13 stores at least a boot program for starting the computer system. The RAM 14 has a program area for temporarily storing a program running on the computer system and a data area for writing and reading data. The external storage unit 15 stores an image processing program for generating an evaluation image. Examples of the external storage unit 15 include a hard disk drive, a flexible disk drive, a magneto-optical disk drive, a CD-ROM drive, a CD-R drive, a CD-RW drive, and a DVD (DVD-ROM, DVD-R) drive. The device is applicable. That is, the planning support program is stored in a storage medium such as a CD-ROM that can be removed from each drive, and the computer 1 can read the program stored in the storage medium and execute the processing described below. In that case, the storage medium itself is included in the category of the present invention.
[0030]
The input unit 16 is a device such as a keyboard or a mouse that inputs commands and data from the outside. The display unit 17 outputs characters and image data that are arithmetically processed by the image processing unit 18 based on a control command from the CPU 11. Devices such as liquid crystal displays and CRTs. The image processing unit 18 is a device that performs arithmetic processing on image data to be output by the display unit 17. The communication unit 19 is a device for taking image data from the first camera 102 and the second camera 103.
[0031]
<Image processing flow>
Next, image processing performed by the image processing program will be described with reference to FIGS. FIG. 3 is a diagram showing each process performed when the CPU 11 reads out an image processing program stored in the external storage unit 15 and develops and executes it in the program execution area of the RAM 14. FIG. 4 is a diagram illustrating an example of a screen displayed on the display unit 17 when the user generates an evaluation image using the image processing program.
[0032]
First, in step S301, a frame 401 of a moving image shot by the first camera 102 is displayed. Next, in step S302, one frame 402 at the same timing of the moving image shot by the second camera 103 is displayed next to the image displayed in step S301. That is, at this time, two still images 401 and 402 taken by the first camera 102 and the second camera 103 are displayed side by side on the display unit 17. The two still images are taken at the same timing. However, since the first camera 102 has a wider angle of view than the second camera 103, when displayed at the same scale, the image 401 captured by the first camera 102 is displayed larger as shown in the figure. In addition, since the second camera 103 is placed in the photographing vehicle 101, interiors such as pillars, handles, and ceiling of the photographing vehicle 101 are reflected in the image 402 captured by the second camera 103. .
[0033]
Next, in step S303, an area corresponding to the image area of the second camera is selected from the images captured by the first camera. Here, as shown in the figure, it is assumed that the user selects a region by drawing a frame 403 in an image 401 using a mouse or the like.
[0034]
In other words, the image processing program inputs the size and position of the frame 403 in the image 401 via the input unit 16 such as a mouse. Then, in response to selection (clicking) of the “Next” button 404, the size and position of the frame 403 are determined.
[0035]
In response to this, in step S304, the image processing program extracts a partial image surrounded by the frame 403 from the image photographed by the first camera 102 and uses it as a background image for visibility evaluation.
[0036]
That is, a partial image of the visual field area acquired by the second camera is extracted from the image captured by the first camera, and one frame of the background image for evaluation is generated.
[0037]
Next, it progresses to step S305, it is determined whether the next flame | frame exists, and when there exists, it returns to step S301 and performs the process from step S301 to S304 again. In this manner, a background image for visibility evaluation is generated by repeating the processes of steps S301 to S305 for all the captured frames.
[0038]
When a background image for visibility evaluation is generated, it is presumed that the photographed moving image and a computer graphics image (hereinafter referred to as a CG image) representing the interior of the planned vehicle are superimposed and seen from the driver of the planned vehicle. A video for visibility evaluation is generated. Of course, the interior image to be superimposed changes depending on the driver's field of view. That is, it is generated according to the position of the partial image determined in step S303.
[0039]
Here, two-dimensional image data may be superimposed as an interior image. However, if a virtual interior model is generated in a three-dimensional space and projection image data visible from a virtual driver is superimposed, more accurate visibility evaluation can be performed. This is preferable. Specifically, three-dimensional data representing the interior shape of a virtual vehicle to be planned is generated in advance, the virtual driver's field of view is determined according to the position of the partial image, and the three-dimensional data is projected onto the field of view. Interior image data may be generated.
[0040]
In step S301, an image captured by the first camera 102 is simply input and displayed. However, the present invention is not limited to this. If the peripheral image captured by the first camera 102 is corrected according to the difference between the position of the first camera 102 and the viewpoint position of the driver, a more accurate visibility evaluation image can be obtained.
[0041]
In step S303, the image processing program inputs the size and position of the frame 403 in the image 401 from the user via the input unit 16 such as a mouse. However, the present invention is not limited to this. Instead, the size of the frame may be defined in advance, and only the center of the frame may be input.
[0042]
Although the user selects the partial image of the field-of-view area acquired by the second camera from the image captured by the first camera by viewing with the eyes, the present invention is not limited to this. The partial image extraction module of the image processing program may automatically extract the partial image of the view field area acquired by the second camera from the image captured by the first camera. In that case, for example, it is conceivable to use a pattern matching technique. Furthermore, in the step S304, it is also preferable to correct the partial image according to the image position to be cut out.
[0043]
<Evaluation system>
As described above, the image generated by the processing of the flowchart shown in FIG. 3 is displayed, for example, in the evaluation system shown in FIG. 5 and used by a plurality of evaluators to evaluate the visibility of the planned vehicle.
[0044]
The evaluation system shown in FIG. 5A connects a plurality of evaluation terminals 4001 via a network, and collects marks, comments, target still images, and the like input from the respective terminals 4001 in an operator terminal.
[0045]
In the evaluation system shown in FIG. 5B, a simulation image is displayed on the screen 4004 using the projector 4003, and a plurality of evaluators input comments on the evaluation pad 4005 while simultaneously viewing the images. The input comments are collected together with the input timing information in the operator terminal 4002.
[0046]
<Model generation method>
Next, a method for generating a three-dimensional interior image to be superimposed on a background image for visibility evaluation will be briefly described.
[0047]
Of course, it is possible to convert only the interior part of the planned vehicle into 3D data, set the driver's viewpoint, project the field of view from that viewpoint onto a 2D image, and superimpose it on the background image. Now, a case where the entire planned vehicle is converted into three-dimensional data will be described. The positions of pillars and ceilings included in the interior vary greatly depending on the design and size of the entire planned vehicle. In vehicle planning, the size and shape of the entire vehicle can be determined before moving on to interior planning. Because it is general.
[0048]
When generating three-dimensional data of the entire planned vehicle, the following method may be executed using a system similar to the system described in FIG.
[0049]
First, a three-dimensional outline model serving as a base for each vehicle type such as sports, sedan, and truck is prepared in a database. Then, according to the selection of the user (planner), one of the external models is read from the database.
[0050]
Next, the user is prompted to input basic dimension values such as the number of sheets, the sheet position, the total length, the total height, and the total width by displaying an input screen as shown in FIG. In FIG. 6, (a) is a dimension value input table, and (b) and (c) are a vehicle front view image and a side view image for showing corresponding parts of the dimension values input in the input table. . The dimension values that can be entered in this figure are the wheel base 1101, the total width 1102, the total height 1103, the front overhang 1105, the rear overhang 1106, the horizontal position 1107 of the cowl point CW, the vertical position 1108 of the cowl point CW, and the windshield tilt 1109. . Note that the input dimension values are not limited to this, and a plurality of screens similar to those in FIG. 6 are prepared for inputting various other dimension values.
[0051]
When the dimension value is input, the three-dimensional outer shape model read from the database is deformed according to the dimension value such as the total length, the total height, the total width, and the like. In other words, a three-dimensional external model that can be automatically deformed in accordance with these dimension values is prepared in a database. Specifically, the three-dimensional outline model moves following the definition point whose position is defined by the input dimension value and the definition point so that the shape of the vehicle is not unnatural. And a tracking point.
[0052]
Then, the three-dimensional outline model whose shape is roughly determined by the dimension value is displayed as an image as shown in FIG. 7, and the tracking point of the three-dimensional outline model displayed on the image can be freely moved using a pointing device. As a result, the external shape of the planned vehicle is finely adjusted. In FIG. 7, a point indicated by a star is a definition point, and a point indicated by a white circle is a movable follow-up point. Moreover, the line to which the code | symbol was attached | subjected can be translated while maintaining the shape.
[0053]
On the other hand, using the input dimension value, a sheet model representing the layout of the sheet is generated independently of the outer shape model.
[0054]
Furthermore, an interior model that matches the seat position, bonnet height, ceiling height, and the like determined by the external model and the seat model is generated. The interior model includes a handle, meter hood, pillar, and ceiling surface cover, and the design can be freely changed as long as it does not interfere with the seat model or external model. Specifically, several types of handles, mate hoods, etc. are prepared in advance in the database, and the parts that match the concept of the planned vehicle are read and combined, so that the handle position and pillar thickness and so on are not unnatural. An interior model is generated by adjusting the pillar structure and the like.
[0055]
Then, a three-dimensional planned vehicle model as shown in FIG. 8 is generated by combining the externally generated model, the seat model, and the interior model. In this planned vehicle model, the viewpoint position of the driver is roughly defined from the seat position of the driver's seat, but the viewpoint position and line-of-sight direction can be freely set. And according to the driver | operator's viewpoint position and line-of-sight direction which were set, the visual field image which represents a driver | operator's visual field virtually can be produced | generated easily. The view image includes a pillar, a handle, a meter hood, a hood, a driver's arm, and the like, and does not include a landscape image outside the vehicle.
[0056]
Therefore, the above-described two-dimensional live-action landscape image is superimposed on the view field image generated from the three-dimensional planned vehicle model to generate an image for visibility evaluation as shown in FIG. If there is a problem in visibility, the thickness or structure of the pillar included in the interior model, or its color or pattern is changed to improve visibility.
[0057]
<Effect of this embodiment>
As described above, according to the present embodiment, a landscape estimated to be seen by the driver of the planned vehicle can be represented by a live-action image, and combined with a CG image representing the interior of the planned vehicle, The visibility of the planned vehicle can be more accurately evaluated as compared to the case where the landscape image seen from the inside of the vehicle is also a CG image.
[0058]
Also, compared to the case where a full CG three-dimensional space representing roads and streets is generated and the planned vehicle model is driven in that space, only the planned vehicle needs to be made into a three-dimensional model. An image can be easily generated at a relatively low cost.
[0059]
Moreover, since it is only necessary to run the photographing vehicle to acquire the image, it is possible to generate landscape images in various driving environments very easily compared to the case of generating a full CG three-dimensional space. .
[0060]
Since the image for visibility evaluation is generated by superimposing the CG image representing the interior of the planned vehicle and the CG image representing the interior of the planned vehicle so as to evaluate the visibility, the prototype model and the clay model of the interior can be used as in the past. Compared with the case of creating, the time and cost required for vehicle planning can be greatly reduced.
[0061]
(Second Embodiment)
Next, a second embodiment of the present invention will be described with reference to FIG. In the first embodiment, an image that can be seen by the driver is captured by the second camera. However, in this embodiment, the driver himself / herself is photographed by the second camera, and the field of view is determined by an image showing the driver himself / herself. It is different in point to do. Other configurations and processes are the same as those in the first embodiment, and thus description thereof is omitted.
[0062]
In FIG. 6, since the photographing vehicle 101 and the first camera 102 are the same as those in the first embodiment, the description thereof is omitted here. However, the second camera 601 is fixed to the photographing vehicle 101 and photographs the driver's head. On the other hand, a marker 602 serving as a reference indicating a change in the orientation of the head is attached to the driver's forehead (for example, a helmet worn by the driver). Then, by analyzing the movement of the marker in the image captured by the second camera 601, it is determined which partial image should be extracted from the image captured by the first camera 102. That is, in this embodiment, a driver | operator's visual field area | region is detected from a motion of a driver | operator's head.
[0063]
As a result, the processing of step S302 and step S303 in FIG. 3 in the first embodiment can be replaced. That is, in step S302, the position of the marker is displayed on the screen, and in step S303, the position for extracting the partial image is selected from the image captured by the first camera 102 while viewing the position of the marker.
[0064]
In this way, it is possible to obtain the same effect as in the first embodiment.
(Other embodiments)
In addition to the configuration described in the first and second embodiments, a GPS (Global Positioning System) is mounted on the photographing vehicle 101, and simultaneously with photographing with the first camera and the second camera, You may acquire position information.
[0065]
Moreover, in the said 1st, 2nd embodiment, although the camera was used as a device which acquires a driver | operator's viewpoint or view area, this invention is not limited to this, Other devices may be sufficient. For example, if a sensor that detects the movement of the driver's eyeball is used, the driver's field of view can be determined more accurately.
[Brief description of the drawings]
FIG. 1 is a diagram for explaining an imaging system according to a first embodiment of the present invention.
FIG. 2 is a diagram showing a configuration of an image processing system according to the first embodiment of the present invention.
FIG. 3 is a flowchart showing a flow of image processing according to the first embodiment of the present invention.
FIG. 4 is a diagram showing an example of a display screen according to the first embodiment of the present invention.
FIG. 5 is a diagram showing an overview of a visibility evaluation system according to the first embodiment of the present invention.
FIG. 6 is a diagram illustrating an example of a vehicle dimension input screen.
FIG. 7 is a diagram for explaining fine adjustment of an outer shape.
FIG. 8 is a diagram illustrating an example of a three-dimensional planning vehicle model.
FIG. 9 is a diagram illustrating an example of an image for visibility evaluation.
FIG. 10 is a diagram illustrating an imaging system according to a second embodiment of the present invention.

Claims (6)

An image processing method for generating an image for evaluating visibility during driving in a planned vehicle,
A shooting process of shooting a surrounding image of an existing vehicle in which the shooting means is running;
An input step for inputting an area that is estimated to be seen by a driver in order to identify an area to be cut out from a peripheral image photographed in the photographing step;
An extraction unit extracts a partial image from a peripheral image photographed in the photographing step based on the region input in the input step, and generates a background image for visibility evaluation;
A display step for generating and displaying a visibility evaluation image by superimposing the background image generated in the extraction step and a computer graphics image representing the interior of the planned vehicle;
Have
The input step includes
Photographing the driver's line-of-sight direction with a camera attached to the driver's head;
Or
Photographing the driver's head with a camera and detecting the driver's field of view from the movement of the driver's head;
An image processing method comprising: The photographing step is a step of photographing a peripheral image of the existing vehicle with a peripheral photographing camera attached to an external surface of the existing vehicle,
The said extraction process includes the process of correct | amending the periphery image image | photographed at the said imaging | photography process according to the difference in the position of the said camera for periphery imaging | photography and the said driver | operator's viewpoint. Image processing method. A simulation device for evaluating visibility during driving in a planned vehicle,
First input means for inputting a peripheral image photographed by a peripheral photographing camera attached to an existing vehicle;
A second input means for inputting an area estimated to be seen by a driver in order to identify an area to be cut out from the peripheral image input by the first input means;
An extraction means for extracting a partial image of the visual field input by the second input means from the peripheral image input by the first input means, and generating a background image for visibility evaluation;
Display means for generating and displaying an image for visibility evaluation by superimposing the background image generated by the extraction means and a computer graphics image representing the interior of the planned vehicle;
Have
The second input means includes
Means for photographing the gaze direction of the driver by a camera attached to the driver's head;
Or
Means for photographing the driver's head with a camera and detecting the driver's field of view from the movement of the driver's head;
The simulation apparatus characterized by including. 4. The apparatus according to claim 3, further comprising a unit that corrects the peripheral image input by the first input unit according to a difference in position between the peripheral photographing camera and the viewpoint of the driver. Simulation device. A program for causing a computer to function as a simulation device for evaluating visibility during driving in a planned vehicle,
In the computer,
First input means for inputting a running peripheral image taken by a camera attached to an existing vehicle;
A second input means for inputting an area estimated to be seen by a driver in order to identify an area to be cut out from the peripheral image input by the first input means;
Extraction means for extracting a partial image of the visual field input by the second input means from the peripheral image input by the first input means, and generating a background image for visibility evaluation;
Display means for generating and displaying an image for visibility evaluation by superimposing the background image generated by the extraction means and a computer graphics image representing the interior of the planned vehicle;
Is a program that realizes the functions
The second input means includes
Means for photographing the gaze direction of the driver by a camera attached to the driver's head;
Or
Means for photographing the driver's head with a camera and detecting the driver's field of view from the movement of the driver's head;
The program characterized by including.   A computer-readable storage medium storing the program according to claim 5.

Images