JP6182930B2 - Depth production support device, depth production method, and program - Google Patents

Description

  The present invention relates to a depth production support apparatus that produces a depth image used by a parallax image generation apparatus that generates a parallax image for realizing stereoscopic vision.

  Conventional three-dimensional video display systems are roughly classified into a two-parallax system and a multi-parallax system having three or more parallaxes. In either method, it is necessary to prepare a video in which the scene is viewed from the required number of viewpoints.

  As the most direct video production method, there can be considered a method in which cameras for the required number of parallaxes are prepared and the same scene is shot with a plurality of cameras arranged at predetermined intervals. Recently, cameras that can directly shoot two parallaxes are commercially available, but cameras that can directly shoot multiple parallaxes are not common.

  A method of creating a three-dimensional CG (Computer Graphics) image and setting a plurality of camera positions for rendering is also conceivable. The three-dimensional CG image includes depth information, and a parallax image corresponding to the multi-parallax method can be created from the three-dimensional image. However, when the number of camera positions is large, there is a problem that the number of renderings increases, which takes time and cost. Furthermore, most videos are not CG images but are real photographs, and it is required to create a three-dimensional video from the real photographs.

  There are several methods (so-called two-dimensional / three-dimensional conversion methods) for converting a multi-parallax image based on a plane (2D) image to produce a multi-parallax image based on a real image. However, there is no depth information in the method of converting to a multi-parallax image. Therefore, it is necessary to create depth information one by one in every scene (frame), and the work load is very high.

  Thus, as a method for setting the depth value, for example, Patent Document 1 proposes a technique for changing the mesh shape in accordance with a user instruction and setting the depth value. Patent Document 2 proposes a technique for drawing a contour line in accordance with a user instruction and setting a depth value for the contour line. Non-Patent Document 1 proposes a technique in which a user moves and rotates a selected portion of a video in a three-dimensional space to set a depth value.

  However, the technique described in Patent Document 1 has a problem that there are many items to be operated, and it takes a long time to set the depth information for one frame, and it is difficult to confirm the set depth value. Further, the technique described in Patent Document 2 not only takes a long time to draw contour lines and set depth information, but also makes it difficult to draw contour lines when the subject has a complicated shape. was there. Further, although the technique described in Non-Patent Document 1 has a simplified setting method, there is a problem in that the positional relationship is likely to be inconsistent because depth values in different frames cannot be compared.

  In view of this, the present inventors disclosed in Patent Document 3 (1) a technique for setting a depth value using a graph and a slide bar, (2) a technique for checking a depth value using a graph and a preview screen, ( 3) A technique for interpolating depth values between key frames, and (4) a technique for generating a depth image and a label image based on the above-described technique are proposed.

  Furthermore, the present applicant has proposed a technique for producing a depth image expressing local irregularities in Patent Document 4 and Patent Document 5.

Special table 2010-516155 gazette Special table 2011-523323 gazette Japanese Patent Application No. 2011-168920 Japanese Patent Application No. 2012-069923 Japanese Patent Application No. 2012-222840

DepthDirector: A System for Adding Depth to Movies

  However, the techniques described in Patent Document 1 and Patent Document 2 have a conventional problem that there are many items to be operated and it takes a long time to set depth information for one frame. Further, in the technique described in Patent Document 3, there remains a problem that the local protrusion of the mask region cannot be expressed. However, the technique described in Patent Document 4 solves this problem.

  However, in the technique described in Patent Document 4, a depth image expressing local unevenness of a still image is produced. Therefore, the technique described in Patent Document 4 can be applied to a moving image, but it takes a lot of time to manually set depth information for each frame, and the work load becomes very high. was there. This problem is solved by the technique described in Patent Document 5.

  In the technique described in Patent Document 5, when setting a depth value to a one-stroke outline set for a subject of each frame of a moving image, a small number of representative points (hereinafter referred to as anchor points) of the outline are used. Depth setting is performed by inputting depth values and interpolating between them.

FIG. 16 is a diagram illustrating depth setting by the technique described in Patent Document 5.
FIG. 16A shows a situation where anchor points are set for an image in which the subject moves forward toward the camera from frame a in FIG. 16A to frame b in FIG.

  The depth value ranges from 1 to 255, and is set to increase the depth value by +50 from frame a to frame b. That is, the depth value of the anchor point placed at the fingertip is set to 150 for frame a and 200 for frame b. Here, when the setting is made to further increase the +50 depth value so that the entire subject is further projected in the frame b, it is necessary to change the depth values of all the anchor points in the frame b one by one. There is a problem that it takes time.

  The present invention has been made in view of the above-described problems, and an object of the present invention is to set the depth of a subject outline in a moving image in which the entire subject moves forward and backward toward the camera with a simple operation. It is to provide a depth production support device.

  In order to achieve the above-described object, the first invention is a depth production support apparatus that supports production of a depth image used for generating a parallax image for realizing stereoscopic vision, and which is an original moving image. Mask image input means for reading mask images of a plurality of frames binarized for identifying a specific subject drawn in each frame, and contour line setting means for setting a contour line for the mask image And at least two first frames as keys for the mask images of the plurality of frames, and for each of the first frames, a first depth value that is a uniform value for the entire contour line is set. The base depth value setting means to set, and the first depth value of the frame between the two adjacent first frames, the first depth value set in the two adjacent first frames Or At least two second frames serving as keys are set for the base depth value interpolating means to be obtained by interpolation and the mask images of the plurality of frames, and a plurality of them are provided at corresponding positions on the contour lines of the second frames. Anchor point setting means for setting a first depth point and setting a second depth value representing local irregularities on a contour line to the first point; and to the first point of the second frame Adding the set second depth value and the first depth value of the second frame to determine a final depth value of the first point of the second frame; Depth determining means for obtaining a final depth value at each position on a contour line between adjacent first points of a frame by interpolation from the final depth value of the adjacent first points. Depth production support equipment It is.

According to the first invention, it is possible to set the depth of the subject outline in a moving image with a simple operation.
For example, for a moving image in which the entire subject advances toward the camera or moves away from the camera, a uniform first depth value is set for the contour of the subject by the base depth value setting means, and the anchor point setting means is used. By the simple operation of setting a second depth value representing local irregularities on the contour line to a specific point (first point) on the contour line, the depth determining means The final depth value of the first point is obtained by adding the second depth values, and the final depth value at each position on the contour line can be obtained by interpolation based on this value.

The contour line is preferably a closed curve drawn in one stroke.
The first frame preferably includes a first frame and a last frame of the mask images of the plurality of frames.

The base depth value interpolation means calculates the first depth value set in the two adjacent first frames, the frame between the two adjacent first frames, and the two adjacent first frames. The first depth value of a frame located between the two adjacent first frames is determined by linear interpolation according to the ratio of the interval with one frame.
Further, the depth determining means obtains the final depth value at each position on the contour line between the first points of the second frame by interpolating from the final depth values of the adjacent first points.

  The depth determining means obtains position information of a second point corresponding to the first point set in the second frame of each frame between the adjacent second frames, with the second adjacent point. The position information of the first point of the frame is obtained by linear interpolation according to the ratio of the interval between the two adjacent second frames and the two adjacent second frames, The final depth value of the second point, the final depth value of the first point of the adjacent second frame, the frame between the two adjacent second frames, and the adjacent 2 It is obtained by linear interpolation according to the ratio of the interval between two second frames.

The depth determination means obtains a final depth value at each position on the contour line between two adjacent second points based on the final depth value of the adjacent second points.
This makes it possible to determine final depth values at all positions on the contour line of the mask image of all frames.

The depth determining means is configured so that an inner region of the contour line is a smooth plane based on the final depth value of the first point and the final depth value of each position on the contour line between the first points. The depth value of each pixel of the mask image is calculated to create the depth image.
As a result, the final depth value of all pixels of the mask image of all frames is obtained, and the depth image can be produced.

  According to the first invention, in the moving image in which the entire subject moves forward toward the camera or moves away from the camera, the first depth value is set for the movement of the entire subject, and the second local unevenness on the contour line is set. By setting the depth value, the movement of the entire subject and the depth of the local unevenness can be set separately, and the depth value of the point on the contour line of each frame can be set with the movement of the entire subject and the local unevenness. This makes it possible to create depth images with simple operations, eliminating the need to input each item.

  A second invention is a depth production method for producing a depth image to be used for generating a parallax image for realizing stereoscopic vision, wherein the computer is drawn in each frame of the original moving image. A mask image input step for reading a mask image of a plurality of frames binarized to identify a subject, a contour line setting step for setting a contour line for the mask image, and a mask image of the plurality of frames On the other hand, a base depth value setting step for setting at least two first frames as keys and setting a first depth value that is a uniform value for the entire contour line for each of the first frames; The first depth value of a frame between two adjacent first frames is interpolated from the first depth value set in two adjacent first frames. Base depth value interpolation step, and at least two second frames as keys for the mask images of the plurality of frames, and a plurality of frames at corresponding positions on the contour lines of the second frames. An anchor point setting step of setting a first point and setting a second depth value representing a local unevenness on a contour line at the first point, and setting to the first point of the second frame The second depth value that has been generated and the first depth value of the second frame are added to determine the final depth value of the point of the second frame, and adjacent to the second frame A depth determination step of performing a depth determination step by interpolating a final depth value of each position on the contour line between the first points from the final depth value of the adjacent first points. Is the method.

  A third invention is a program for causing a computer to function as a depth production support apparatus that supports production of a depth image used for generation processing of a parallax image for realizing stereoscopic vision. Mask image input means for reading mask images of a plurality of frames binarized to identify a specific subject drawn in each frame of the moving image, and a contour line for setting a contour line for the mask image At least two first frames as keys are set for the setting hand and the mask images of the plurality of frames, and a first depth which is a uniform value for the entire contour line is set for each first frame. Base depth value setting means for setting a value, and setting the first depth value of a frame between two adjacent first frames to two adjacent first frames. Base depth value interpolating means that is obtained by interpolation from the first depth values, and setting at least two second frames as keys for the mask images of the plurality of frames, and for each of the second frames Anchor point setting means for setting a plurality of first points at corresponding positions on the contour line, and setting a second depth value representing local irregularities on the contour line at the first point, the second frame The second depth value set at the first point of the first frame and the first depth value of the second frame are added to obtain the final depth value of the first point of the second frame. Depth determining means for determining and determining the final depth value at each position on the contour line between the adjacent first points of the second frame by interpolation from the final depth value of the adjacent first points; To function as Is a program.

  According to the present invention, it is possible to provide a depth production support device and the like that can set the depth of a subject outline in a moving image in which the entire subject moves forward and backward toward the camera with a simple operation.

The figure which shows the structural example of the hardware of the depth production assistance apparatus 1 which concerns on embodiment of this invention. The figure which shows the input-output data of the depth production assistance apparatus 1 and a parallax image generation apparatus Flow chart showing the flow of depth production support processing for moving images The figure which shows the input data to the depth production assistance apparatus 1 The figure which shows an example of the two-dimensional image 31 used as the process target of the depth production assistance apparatus 1 The figure which shows an example of the mask image 51 produced from the two-dimensional image 31 The figure which shows an example of the outline 61 set to the mask image 51 Illustration of the mask image of the subject moving forward toward the camera The figure which shows an example of the base depth value setting screen 70 Diagram explaining how to set the base depth value The figure which shows an example of the base depth value setting data 80 The figure which shows an example of the base depth value data 85 The figure which shows an example of the anchor point setting screen 90 The figure explaining the depth value setting method by the depth production assistance apparatus 1 of this embodiment. The flowchart which shows the detail of a process of a depth determination process (step 6 of FIG. 3). The figure explaining the conventional depth value setting method

  DESCRIPTION OF EMBODIMENTS Hereinafter, preferred embodiments of an etching rate measuring apparatus according to the present invention will be described in detail with reference to the accompanying drawings.

  FIG. 1 is a hardware configuration diagram of a contour corresponding point determination support apparatus 1 according to an embodiment of the present invention. Note that the hardware configuration in FIG. 1 is an example, and various configurations can be adopted depending on applications and purposes.

  The contour corresponding point determination support device 1 includes a control unit 11, a storage unit 12, a media input / output unit 13, a communication control unit 14, an input unit 15, a display unit 16, a peripheral device I / F unit 17, etc. Connected through.

  The control unit 11 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like.

  The CPU calls and executes a program stored in the storage unit 12, ROM, recording medium, etc. to a work memory area on the RAM, drives and controls each device connected via the bus 18, and determines contour corresponding points. The below-mentioned process which the assistance apparatus 1 performs is performed. The ROM is a non-volatile memory, and permanently stores a boot program, a program such as BIOS, data, and the like of the contour corresponding point determination support device 1. The RAM is a volatile memory, and temporarily stores programs, data, and the like loaded from the storage unit 12, ROM, recording medium, and the like, and includes a work area used by the control unit 11 for performing various processes.

  The storage unit 12 is an HDD (hard disk drive) or the like, and stores a program executed by the control unit 11, data necessary for program execution, an OS (operating system), and the like. As for the program, a control program corresponding to an OS (operating system) and an application program for causing the contour corresponding point determination support apparatus 1 to execute processing described later are stored. Each of these program codes is read by the control unit 11 as necessary, transferred to the RAM, read by the CPU, and executed as various means.

  The media input / output unit 13 (drive device) inputs / outputs data, for example, media such as a CD drive (-ROM, -R, -RW, etc.), DVD drive (-ROM, -R, -RW, etc.) Has input / output devices.

  The communication control unit 14 includes a communication control device, a communication port, and the like, and is a communication interface that mediates communication between the contour corresponding point determination support device 1 and the network, and communicates with other devices via the network. Take control. The network may be wired or wireless.

  The input unit 15 inputs data and includes, for example, a keyboard, a pointing device such as a mouse, and an input device such as a numeric keypad. Through the input unit 15, an operation instruction, an operation instruction, data input, and the like can be performed on the contour line corresponding point determination support device 1.

  The display unit 16 includes a display device such as a CRT monitor and a liquid crystal panel, and a logic circuit or the like (video adapter or the like) for realizing the video function of the contour corresponding point determination support device 1 in cooperation with the display device.

  The peripheral device I / F (interface) unit 17 is a port for connecting a peripheral device to the contour corresponding point determination support device 1, and the contour corresponding point determination support device 1 through the peripheral device I / F unit 17. Sends and receives data to and from peripheral devices. The peripheral device I / F unit 17 is configured by USB, IEEE 1394, RS-232C, or the like, and usually includes a plurality of peripheral devices I / F. Connection with peripheral devices Cellphones may be wired or wireless.

  The bus 18 is a path that mediates transmission / reception of control signals, data signals, and the like between the devices.

  FIG. 2 is a diagram illustrating input / output data of the depth production support apparatus 1 and the parallax image generation apparatus 2. As shown in FIG. 2, the depth production support apparatus 1 receives a two-dimensional image 3, a background image 4, a mask image 5, a contour line 6, and a depth value 7 as input data, and outputs a depth image 8 and a label image 9. Data. The parallax image generation device 2 uses the two-dimensional image 3, the depth image 8, and the label image 9 as input data, and uses the parallax image 10 as output data.

The two-dimensional image 3, the background image 4, the mask image 5, and the contour line 6 may be generated by the control unit 11 (hereinafter, abbreviated as “control unit 11”) of the depth production support apparatus 1, You may acquire from the outside via the output part 13, the communication control part 14, etc.
In the portable depth production support apparatus 1 of the present embodiment, the depth value 7 is input by inputting the depth value 7 for a small number of frames and a few points on the contour line via the input unit 15. The device 1 generates depth values 7 for points on other frames and other contour lines. Details will be described later.

  The two-dimensional image 3 is a frame image or a still image for one moving image (planar image). A moving image (planar image) includes, for example, a color still image of a predetermined number of frames per unit time (usually 30 frames per second), and each pixel has 256 gradations of RGB.

  The background image 4 is an image showing a sense of depth in the background. The background image 4 may be generated manually using photo retouching software or the like based on the two-dimensional image 3, or may be automatically generated using separate software.

  The mask image 5 is a binarized image for identifying a specific subject. The mask image 5 may be generated manually using photo retouching software or the like based on the two-dimensional image 3, or may be automatically generated using separate software.

  The contour line 6 is a line indicating a binary boundary of the mask image 5. The contour line 6 may be generated by the control unit 11 performing a contour line detection process, or may be input by the user using a mouse or the like.

  The depth value 7 is a value that defines the position of the subject in the depth direction. In the present invention, a range of pixel values having a depth value of 7 is expressed as 256 gradations from 0 to 255. 0 corresponds to black, 255 corresponds to white, and 1 to 254 correspond to gray (halftone). Base depth values set for a small number of frames of the mask image by the user's input operation, and depth values of local unevenness set for several points (hereinafter referred to as anchor points) along the contour 6 Is input, the control unit 11 calculates and sets the depth value 7 of each pixel in the inner region of the contour line 6.

  The depth production support device 1 supports production of the depth image 8 based on the two-dimensional image 3, the background image 4, the mask image 5, the contour line 6, and the depth value 7. In particular, the depth production support apparatus 1 according to the embodiment of the present invention is characterized in that the depth value of a three-dimensional object (subject) that moves forward toward the camera or moves backward away from the camera can be easily set. There is.

  The depth image 8 is an image in which the depth value from the camera to the subject related to the two-dimensional image 3 is replaced with a pixel value. Here, the camera means a virtual camera defined in the internal processing of the parallax image generation device 2.

  The depth image 8 is, for example, a gray scale with a pixel value range of 0 to 255 (8 bits), and 0 (black) is the farthest and 255 (white) is often the foreground. There may be. In the following, in order to make the explanation easy to understand, the depth image 8 has a pixel value range of 0 to 255, 0 (black) being the deepest and 255 (white) being the foremost.

  The label image 9 is associated with each two-dimensional image 3, and is divided into regions by unique numerical values (label values) for identifying subjects constituting the scene recorded in the two-dimensional image 3, and the label values are represented by pixel values. This is an image replaced (labeled) with. For example, in a scene composed of a background, a building, and a person, L0, L1, and L2 are assigned as label values corresponding to the background, the building, and the person, respectively, and each pixel of the corresponding two-dimensional image 3 is assigned to which subject. Whether it belongs or not is expressed by replacing it with pixel values of L0, L1, and L2.

  The label image 9 may be generated manually using photo retouching software or the like based on the two-dimensional image 3, or may be automatically generated by the depth production support apparatus 1 as in the present invention.

  The parallax image 10 is an image for realizing stereoscopic viewing. In the embodiment of the present invention, the parallax image 10 is an image for realizing stereoscopic vision by naked-eye observation, particularly using binocular parallax (about 60 mm to 70 mm).

  Although not described in detail in the embodiment of the present invention, a plurality of parallax images 10 are synthesized in accordance with the specifications of the display, and displayed on the display, it is possible to realize stereoscopic vision by naked eye observation. . A known technique may be used for the synthesis process of the plurality of parallax images 10.

  The parallax image generating device 2 generates a parallax image 10 based on the two-dimensional image 3, the depth image 8, and the label image 9. Details of the parallax image generating device 2 are described in Japanese Patent Application Nos. 2010-176864 and 2011-55878, which were previously filed by the present applicant.

  FIG. 3 is a flowchart for explaining the flow of a depth creation support process for moving images executed by the depth creation support apparatus 1.

In step 1, the control unit 11 (hereinafter also referred to as the control unit 11) of the depth production support apparatus 1 reads an input image group (moving image) based on an instruction from the user.
In step 2, when contour extraction is instructed by the user, the control unit 11 detects the contour of the mask image 5 and draws the contour line 6 on the mask image. The contour line 6 is a closed curve drawn with one stroke. As a method for detecting the contour line 6, for example, a general method of recognizing an edge (boundary) based on a change in pixel value may be used. The contour line 6 may be input by the user using the input unit 15 such as a mouse, or may be obtained by changing the shape of the locus.

Next, the control unit 11 sets a base depth value 83 in step 3.
The setting of the base depth value 83 (step 3) is a characteristic processing configuration of the depth production support apparatus 1 of the present embodiment.
The base depth value 83 is a depth value that is once set uniformly on the contour line 6 of the subject, and determines the position of the entire subject in the depth direction. The control unit 11 displays a screen for supporting the setting of the base depth value 83 for a small number of frames on the display unit 16 and allows the user to input.
The setting of the base depth value 83 will be described later.

  Next, in step 4, the control unit 11 obtains the base depth values 83 of all the frames by interpolation based on the base depth values 83 for the small number of frames set in step 3.

  Next, in step 5, the control unit 11 sets corresponding points (hereinafter referred to as anchor points) on a small number of frames, and sets depth values representing local irregularities of the contour line of the mask image. The control unit 11 displays a screen that supports the input of the anchor point and the depth value of the anchor point on the display unit 16 and allows the user to input the screen.

  Next, in step 6, based on the base depth value 83 obtained by the base depth value interpolation process in step 4 and the anchor point setting process in step 5 and the depth value representing local unevenness, For all frames, the final depth values of all points on the contour line are calculated, and depth images are created.

The moving picture depth production support process shown in FIG. 3 will be described in detail below.
FIG. 4 is a diagram for explaining an input image group handled by the depth production support apparatus 1.

As shown in FIG. 4, the input image group includes a two-dimensional image, n mask images of subjects 1 to n, and a background image for each frame. The number n of mask images corresponds to the number of three-dimensional objects (subjects) appearing in the moving image. The background image is an image of a portion excluding a three-dimensional object (subject) in the two-dimensional image.
For example, when the number of frames is 1000, 1000 two-dimensional images, n × 1000 mask images, and 1000 background images are prepared.

FIG. 5 is a diagram illustrating an example of a two-dimensional image 31 for one frame that is input to the depth production support apparatus 1 in step 1 of FIG. 3.
Since the two-dimensional image 31 shown in FIG. 5 is composed of a single three-dimensional object (subject), one frame of the input image group includes a two-dimensional image, one mask image, and a background image.
In the two-dimensional image 31 shown in FIG. 5, a male subject extends his arm in the camera direction with his left hand and points a finger.

FIG. 6 is a diagram showing a mask image 51 of the two-dimensional image 31 shown in FIG. 5 that is input to the depth production support apparatus 1 in step 1 of FIG.
Since the mask image 51 has no information about the depth, the direction of the subject and the direction of pointing the finger are unknown. Therefore, the depth image production support apparatus 1 performs the process of setting the depth value 7 of the mask image 51 and creating the depth image 8 as described later.

  FIG. 7 shows the contour line 61 detected by the control unit 11 for the mask image 51 in step 2 of FIG. The contour 61 can be obtained using a general method for recognizing an edge portion where the pixel value of the mask image 51 changes, and is a closed curve drawn with one stroke.

The control unit 11 obtains contour lines for all frames of the same subject in step 2 of FIG.
FIG. 8 is a diagram showing an example of contour lines of two different frames (frame a and frame b) of the same subject as the mask image 51 shown in FIGS.

The contour line in FIG. 8 shows an example in which a man with the arm shown in FIG. 5 pointing forward and pointing forward advances from the position far from the camera in frame a toward the camera in frame b. Yes.
In such a case, the subject similarly puts his arm forward and points forward, but the entire subject is far away from the camera in frame a and at a deep depth position, and in frame b, the depth is It is in a shallow front position.

Next, the control unit 11 sets a base depth value in step 3 of FIG.
The base depth value is a value representing the depth of the entire subject as shown in FIG.

In step 3 of FIG. 3, the control unit 11 first displays a screen for setting the base depth value on the display unit 16.
FIG. 9 is a diagram illustrating a base depth value setting screen example 70.

As shown in FIG. 9, the base depth value setting screen 70 includes, for example, a mask selection pull-down 71, an image display area 72, a base depth value setting area 73, a key frame setting button 77, a key frame selection button 78, and a key frame. It includes a delete button 79, a base depth value setting button 65, an end button 66, and the like.
The base depth value setting area 73 includes a base depth value display area 76, a frame selection slider 74, a base depth value setting slider 75, and the like.

The base depth value display area 76 displays the base depth value set with the horizontal axis as the frame number and the vertical axis as the base depth value.
The base depth value on the vertical axis can take values from 1 to 255, with 1 being the farthest and 255 being the foremost.

The mask selection pull-down 71 is a pull-down menu for selecting the mask image 5 for setting the base depth value, and displays an identification number or the like attached to the mask image for the currently processed moving image. It is possible to choose.
As shown in FIG. 4, when a two-dimensional image of a moving image to be processed includes n subjects and there are n mask images, the mask selection pull-down 71 displays the identification numbers of the n mask images. And let the user select one of them.

In the image display area 72, a mask image of the frame selected by the frame selection slider 74 of the mask image selected by the mask selection pull-down 71 is displayed.
The user can determine a frame (hereinafter referred to as a base depth value setting key frame) for setting a base depth value while sliding the frame selection slider 74 while viewing the mask image displayed in the image display area 72. Is possible.

The base depth value setting key frame can be determined by sliding the frame selection slider 74 to a desired position and clicking the key frame setting button 77 with a mouse or the like.
Next, the base depth value of the determined base depth value setting key frame is slid by sliding the base depth value setting slider 75 to a desired position and clicking the base depth value setting button 65 with a mouse or the like. Can be determined.

  In order to display the mask image of the key frame that has already been set in the image display area 72, the key frame selection button 78 is operated. In addition, when it is desired to delete the base depth value setting key frame, the frame selection slider 74 is slid to the position of the key frame to be deleted, or the key frame selection button 78 is used to match the position of the base depth value setting key frame. The key frame deletion button 79 may be clicked.

  The base depth value setting screen 70 in FIG. 9 is an example, and the configuration of the screen is not limited to this.

  10 shows a portion of the base depth value setting area 73 when setting the base depth values of the two frames (frame a and frame b) in FIG. 8, and FIG. 11 shows an example of the base depth value setting data 80. Show.

As shown in FIG. 10A, in the frame b (frame number 32) in which the base depth value of the frame a (frame number 22) with the subject in the back is set to 100, for example, and the subject is moving forward, As shown in FIG. 10B, the base depth value is set to 150, for example.
The set base depth value is stored in the storage unit 12 together with the base depth setting key frame number.

That is, as shown in FIG. 11, the base depth value is stored in the storage unit 12 as base depth value setting data 80.
The base depth value setting data 80 includes, for example, a mask image identification number 81, a base depth value setting key frame number 82, and a base depth value 83.

In the example of FIG. 11, for the mask image 1, the base depth value 83 is set for the six base depth value setting key frames 82.
As described above, the position in the depth direction of the entire subject is determined for a small number of base depth value setting key frames 82 by the base depth value setting process in step 3 of FIG.

  Next, the control unit 11 performs, based on the base depth value setting data 80 stored in the storage unit 12 by the base depth value interpolation processing in step 4 of FIG. Ask for.

That is, the base depth value 83 for each frame 84 between two adjacent base depth value setting key frames 82 is interpolated using the base depth value 83 set by the two adjacent base depth value setting key frames 82. Ask.
For example, in the example of FIG. 11, when obtaining the base depth value 83 for the frame numbers 23 to 31 that are between two adjacent base depth value setting key frame 82 numbers “22” and “32”, By using “100” and “150”, which are the base depth values 83 of the value setting key frames “22” and “32”, linearly according to the ratio between the frame number to be calculated and the number of both base depth value setting key frames. What is necessary is just to obtain by interpolation.

  The base depth value 83 for all the frames between the base depth value setting key frames stored in the storage unit 12 as the base depth value setting data 80 is obtained by the base depth value interpolation processing in step 4 of FIG. The data 85 is stored in the storage unit 12.

As shown in FIG. 12, the base depth value data 85 includes a mask image identification number 81, a frame number 84, and a base depth value 83.
Based on the base depth value interpolation process (step 4 in FIG. 3), the base depth value 83 is obtained for all frames including the mask image of the specific subject.

  Next, the control unit 11 executes anchor point setting processing in step 5 of FIG. That is, the anchor point setting screen 90 is displayed on the display unit 16 and the user sets an anchor point.

FIG. 13 is a diagram illustrating an example of the anchor point setting screen 90.
In the example shown in FIG. 13, the anchor point setting screen 90 includes a mask selection pull-down 91, an image display area 92, an anchor point setting area 93, a frame selection slider 94, a key frame setting button 96, a key frame deletion button 97, A key frame selection button 98, an end button 99, and the like are included.

The anchor point setting area 93 includes an anchor point depth setting slider 86, a depth value display section 87, a setting button 88, a deletion button 89, and the like.
The anchor point setting screen 90 of FIG. 13 is an example, and the configuration of the screen is not limited to this.

  The mask selection pull-down 91 is a pull-down menu for selecting a mask image 5 for setting an anchor point, and displays an identification number or the like attached to the mask image for the currently processed moving image. It is possible to select.

In the image display area 92, the mask image of the frame selected by the frame selection slider 94 of the mask image 5 selected by the mask selection pull-down 91 is displayed.
The user can determine a frame for setting an anchor point (hereinafter referred to as an anchor point setting key frame) while viewing the mask image displayed in the image display area 92 by sliding the frame selection slider 94. is there.

An anchor point setting key frame can be determined by sliding the frame selection slider 94 to a desired position and clicking the key frame setting button 96 with a mouse or the like.
In the example of FIG. 13, the frame selection slider 94 is slid to use the frame 32 as an anchor point setting key frame.
When the determined anchor point setting key frame is determined, the mask image of the anchor point setting key frame is displayed in the image display area 92 along with the outline.

Next, the control part 11 sets the anchor point for expressing a local unevenness | corrugation on this outline. That is, an anchor point is set by placing the cursor on a local uneven portion on the contour line with a mouse or the like and clicking.
The anchor point is displayed in the image display area 92 by, for example, a circle as shown in FIG.

  In the example of FIG. 13, counterclockwise from the lower right end of the contour line, anchor points at the lower part of the arm, the little finger side of the back of the hand, the tip of the index finger, the base of the thumb, the base of the neck, the base of the neck on the opposite side Is set.

Next, the depth value of each anchor point is input using the anchor point depth setting slider 86 in the anchor point setting area 93.
The depth value of the anchor point takes a value of −255 to +255, and represents the degree of unevenness with respect to the base depth value uniformly given to the previously determined contour line.

  After determining the position of the anchor point on the contour line displayed in the image display area 92, the depth value is set by sliding the anchor point depth setting slider 86 to a desired position and clicking the setting button 88. You just have to do it. The depth value display portion 87 displays the depth value of the slide position of the anchor point depth setting slider 86.

  In the example of FIG. 13, the depth value of the anchor point is set for the anchor point whose position has been previously set, and “0” is set to the anchor point in the lower part of the arm counterclockwise from the lower right end of the contour line. "80" for the little finger side anchor point, "100" for the index point at the tip of the index finger, "80" for the anchor point at the base of the thumb, "0" for the anchor point at the base of the neck, and the base of the neck on the opposite side A depth value of “0” is set at the anchor point.

  The control unit 11 stores the set position information of the anchor point and the depth value of the anchor point in the storage unit 12 as anchor point information together with the identification number of the mask image and the frame number of the key frame of the anchor point.

The key frame deletion button 97 is clicked when deleting an already set anchor point setting key frame.
The key frame selection button 98 is clicked when selecting an already set anchor point setting key frame.

The anchor point is provided at a corresponding position on the contour line of at least two key frames.
FIG. 14 is a diagram illustrating the depth value setting of the anchor point for the mask image in which the subject advances in the camera direction from frame a to frame b in FIG.

  For the frame a in FIG. 14A, the previously set base depth value “100” has already been set, and by the anchor point setting process (step 5 in FIG. 3), "0" for the anchor point on the lower part of the arm, "80" for the little finger on the back of the hand, "100" for the anchor point on the tip of the index finger, "80" for the anchor point at the base of the thumb, the base of the neck A depth value of “0” is set to the anchor point of “0”, and a depth value of “0” is set to the anchor point at the base of the opposite neck.

Also in the frame b in FIG. 14B in which the subject has advanced in the camera direction, the anchor point is set at a position corresponding to the position of the anchor point in the frame a. "0" for the anchor point, "80" for the little finger on the back of the hand, "100" for the tip of the index finger, "80" for the anchor point at the base of the thumb, "0" for the anchor point at the base of the neck ", A depth value of" 0 "is set at the anchor point at the base of the opposite neck.
In frame b in FIG. 14B, the base depth value “150” set in advance is already set.

In the case of FIG. 14, the shape of the contour line pointing up from the frame a to the frame b has not changed, so the position of the anchor point in the frame a in FIG. 14A and the frame b in FIG. Depth values are the same.
When the shape of the contour changes as the frame progresses, the position of the anchor point may be set to a corresponding position on the contour of the key frame, and the depth value of the anchor point may be set to a different value. .

  As described above, anchor point setting processing (step 5 in FIG. 3) sets anchor points at a plurality of corresponding positions on the outline of the key frame of the plurality of anchor points, and sets the depth values of the anchor points. Is done.

  Next, in step 6 in FIG. 3, the control unit 11 obtains a final depth value based on the base depth value set in steps 3 to 5 and the depth value of the anchor point, and generates a depth image 8. .

FIG. 15 is a flowchart showing the flow of the depth determination process in step 6 of FIG.
First, the control unit 11 obtains a final depth value for the anchor point set in the key frame of each anchor point (step 61).

That is, with reference to the base depth value data 85 as shown in FIG. 12, the base depth value 83 is read for the frame 84 of the key frame of the anchor point, and the depth of each anchor point set in the anchor point setting process in step 5 Add the value to calculate the final depth value for each anchor point.
Thus, the final depth value of each anchor point in the key frame of each anchor point is obtained.

Next, in step 62, the control unit 11 calculates the final depth value of each point on the contour line between adjacent anchor points for each key frame of each anchor point by interpolation processing from the final depth value of the adjacent anchor points. To do.
Thereby, the final depth value of the outline of the key frame of each anchor point is determined.

Next, in step 63, the control unit 11 calculates the depth value of each point on the contour line for each frame between the key frames of adjacent anchor points.
That is, first, the position of the point corresponding to the anchor point is obtained on the outline of each frame. This can be obtained by interpolating the position information of the anchor point in the key frame of the anchor point on both sides of the frame by the ratio of the number of frames from the target frame to both key frames.

Next, the final depth value of the point corresponding to the anchor point is obtained. This can be obtained by interpolating the final depth value of the anchor point corresponding to the key frame of the anchor point on both sides of the frame by the ratio of the number of frames from the target frame to both key frames.
Finally, based on the final depth values of the points corresponding to the adjacent anchor points, the final depth values of the points on the contour line between them are obtained.

  In step 63, final depth values of points on the contour line are obtained for all frames.

  Next, in step 64, the control unit 11 calculates the depth value inside the contour line (closed curve) for each frame. For example, the depth value inside the contour line is calculated using the final depth value of each point on the contour line so that the inner region of the contour line draws a smooth plane.

Next, in step 65, the control unit 11 creates and outputs a depth image for each frame from the final depth value on the contour line and the depth value inside the contour line.
Thereby, the depth production support processing of the moving image of the depth production support device 1 of the present embodiment is completed.

  As described above, with the depth production support apparatus 1 of the present invention, the depth value given to the contour line of the mask image can be easily set for a moving image in which the entire subject moves forward in the camera direction and a moving image in which the subject moves backward from the camera direction. It can be set by operation, and moving image processing for realizing stereoscopic viewing can be easily performed.

  As mentioned above, although embodiment of this invention was described referring an accompanying drawing, the technical scope of this invention is not influenced by embodiment mentioned above. It is obvious for those skilled in the art that various modifications or modifications can be conceived within the scope of the technical idea described in the claims, and these are naturally within the technical scope of the present invention. It is understood that it belongs.

DESCRIPTION OF SYMBOLS 1 ......... Depth production assistance apparatus 2 ......... Parallax image generation apparatus 3, 31 ......... Two-dimensional image 5, 51, 81 ......... Mask image 6, 61 ......... Contour line 7 ......... Depth value 8 ......... Depth image 70 ......... Base depth value setting screen 80 ......... Base depth value setting data 82 ......... Base depth value setting key frame 83 ......... Base depth value 85 ......... Base depth value data 90 ... …… Anchor point setting screen

Claims (10)

A depth production support apparatus that supports production of a depth image used for generation processing of a parallax image for realizing stereoscopic vision,
A mask image input means for reading mask images of a plurality of frames binarized to identify a specific subject drawn in each frame of the original moving image;
Contour setting means for setting a contour for the mask image;
At least two first frames serving as keys are set for the mask images of the plurality of frames, and a first depth value that is a uniform value is set for the entire contour line for each of the first frames. Base depth value setting means;
Base depth value interpolating means for interpolating the first depth value of a frame between two adjacent first frames from the first depth value set in the two adjacent first frames When,
For the mask images of the plurality of frames, set at least two second frames as keys, set a plurality of first points at corresponding positions on the contour lines of the second frames, and Anchor point setting means for setting a second depth value representing local irregularities on the contour line at the first point;
The second depth value set at the first point of the second frame and the first depth value of the second frame are added, and the first point of the second frame is added. And determining the final depth value of each position on the contour line between the adjacent first points of the second frame by interpolation from the final depth value of the adjacent first points. Depth determination means to be obtained;
A depth production support device characterized by comprising: The depth production support apparatus according to claim 1, wherein the contour line is a closed curve drawn in one stroke. The depth production support apparatus according to claim 1, wherein the first frame includes a first frame and a last frame of the mask images of the plurality of frames. The base depth value interpolation means calculates the first depth value set in the two adjacent first frames, the frame between the two adjacent first frames, and the two adjacent first frames. 4. The first depth value of a frame between the two adjacent first frames is determined by linear interpolation according to a ratio of an interval with one frame. Depth production support device described in 1. The depth determining means obtains the final depth value at each position on the contour line between the first points of the second frame by interpolating from the final depth values of the adjacent first points. The depth production support apparatus according to claim 1 or 2. The depth determining means obtains position information of a second point corresponding to the first point set in the second frame of each frame between the adjacent second frames, with the second adjacent point. The position information of the first point of the frame is obtained by linear interpolation according to the ratio of the interval between the two adjacent second frames and the two adjacent second frames, The final depth value of the second point, the final depth value of the first point of the adjacent second frame, the frame between the two adjacent second frames, and the adjacent 2 The depth production support apparatus according to claim 1, wherein the depth production support apparatus is obtained by performing linear interpolation according to a ratio of an interval between two second frames. The depth determination means obtains a final depth value at each position on a contour line between two adjacent second points based on a final depth value of the adjacent second points. 6. Depth production support apparatus according to 6. The depth determining means is configured so that an inner region of the contour line is a smooth plane based on the final depth value of the first point and the final depth value of each position on the contour line between the first points. The depth production support apparatus according to claim 2 , wherein the depth image is created by calculating a depth value of each pixel of the mask image. A depth production method for producing a depth image used for generating a parallax image for realizing stereoscopic viewing,
Computer
A mask image input step for reading a plurality of binarized mask images for identifying a specific subject drawn in each frame of the original moving image;
An outline setting step for setting an outline for the mask image;
At least two first frames serving as keys are set for the mask images of the plurality of frames, and a first depth value that is a uniform value is set for the entire contour line for each of the first frames. A base depth value setting step;
Base depth value interpolation step for obtaining the first depth value of a frame between two adjacent first frames by interpolation from the first depth values set in the two adjacent first frames When,
For the mask images of the plurality of frames, set at least two second frames as keys, set a plurality of first points at corresponding positions on the contour lines of the second frames, and An anchor point setting step of setting a second depth value representing local irregularities on the contour line at the first point;
The second depth value set at the first point of the second frame and the first depth value of the second frame are added, and the first point of the second frame is added. And determining the final depth value of each position on the contour line between the adjacent first points of the second frame by interpolation from the final depth value of the adjacent first points. A depth determination step to be obtained;
The depth production method characterized by performing. A program for causing a computer to function as a depth production support device that supports production of a depth image used for generation processing of a parallax image for realizing stereoscopic viewing,
Computer
A mask image input means for reading a mask image of a plurality of frames binarized to identify a specific subject drawn in each frame of the original moving image;
An outline setting hand for setting an outline for the mask image;
At least two first frames serving as keys are set for the mask images of the plurality of frames, and a first depth value that is a uniform value is set for the entire contour line for each of the first frames. Base depth value setting means,
Base depth value interpolating means for interpolating the first depth value of a frame between two adjacent first frames from the first depth value set in the two adjacent first frames ,
For the mask images of the plurality of frames, set at least two second frames as keys, set a plurality of first points at corresponding positions on the contour lines of the second frames, and Anchor point setting means for setting a second depth value representing local unevenness on the contour line to the first point,
The second depth value set at the first point of the second frame and the first depth value of the second frame are added, and the first point of the second frame is added. And determining the final depth value of each position on the contour line between the adjacent first points of the second frame by interpolation from the final depth value of the adjacent first points. Depth determining means to be obtained,
Program to function as.

Images