WO2013186881A1

WO2013186881A1 - 3d-image generation method and 3d-image generation system

Info

Publication number: WO2013186881A1
Application number: PCT/JP2012/065143
Authority: WO
Inventors: 勝江畑; 優一宗宮
Original assignee: 株式会社エム・ソフト
Priority date: 2012-06-13
Filing date: 2012-06-13
Publication date: 2013-12-19

Abstract

A 3D-image generation method having a characteristic-information-acquisition step for acquiring characteristic information for each pixel, a depth-information generation step for generating depth information for each pixel on the basis of the characteristic information, and a 3D-image generation step for generating a 3D image on the basis of the depth information. This depth-information generation step establishes an edge between a pair of pixels, sets the overlap information for the edge on the basis of the characteristic information, selects a start pixel from among the pixels, obtains route information by using the overlap information from the start pixel to each pixel, and sets the depth information for each pixel on the basis of the route information. As a result, the provided 3D-image generation method and 3D-image generation system are capable of generating, from an original image, a 3D image causing a viewer to perceive a natural three-dimensional sensation.

Description

Stereoscopic image generation method and stereoscopic image generation system

The present invention relates to a stereoscopic image generation method and a stereoscopic image generation system for generating a stereoscopic image that causes a viewer to perceive a stereoscopic effect by parallax.

In recent years, binocular parallax-type stereoscopic images that allow viewers to perceive a stereoscopic effect by visually recognizing different images for the right eye and the left eye have come to be widely used in fields such as movies and television broadcasting. Yes. In addition, a technique for causing an observer to perceive a stereoscopic effect using a multi-view (multi-viewpoint) stereoscopic image that changes an image viewed by the observer depending on a viewing angle is also used in, for example, an autostereoscopic device. In addition, multi-view parallax stereoscopic images combining these binocular parallax and multi-view types are also being used. In the case of a parallax stereoscopic image, the image is composed of a right-eye image to be visually recognized by the right eye and a left-eye image to be visually recognized by the left eye. By shifting (shifting) in the direction, the viewer (viewer) viewing the image perceives a stereoscopic effect.

Conventionally, a parallax-type stereoscopic image is generally generated by arranging two cameras side by side and simultaneously capturing a right-eye image and a left-eye image. In this case, since a right-eye image and a left-eye image having substantially the same parallax as human binocular parallax can be directly obtained, a natural stereoscopic image that does not give the viewer a sense of incongruity is generated. be able to.

However, in the method of taking the right-eye image and the left-eye image with two cameras in this way, the two cameras having exactly the same specifications are positioned and arranged accurately, and the two are completely synchronized. It is necessary to shoot in the state. For this reason, it is necessary to prepare a large number of special dedicated devices together with specialized staff when shooting, which not only increases the shooting cost but also requires a lot of time to set and adjust the camera and other various devices. It was.

Also, a conventional multi-view stereoscopic image is generally generated by arranging cameras at many viewpoints and simultaneously shooting multi-view images. However, in this method of taking a multi-viewpoint image with a plurality of cameras, a plurality of cameras with exactly the same specifications are positioned and arranged accurately, and all the images are photographed in a completely synchronized state. There was a problem that it was necessary.

Furthermore, when it comes to multi-view parallax stereoscopic video, it is necessary to place two cameras at various viewpoints to shoot video that includes parallax. Therefore, unless there is a very specific purpose, the situation is generally far from widespread.

On the other hand, a method of generating a binocular parallax type image for the right eye and an image for the left eye by performing image processing on an image photographed as usual by one camera (for example, Patent Document 1). In this method, depth information (depth value) is first set for each pixel constituting the original image, and the position of the subject in both images is changed by changing the horizontal position of each pixel according to this depth information. A right-eye image and a left-eye image shifted in accordance with the binocular parallax are generated.

According to this method, since a stereoscopic image can be generated from a normal original image taken by a general camera, the photographing cost can be reduced and the photographing time can be shortened. It is also possible to generate a stereoscopic image from existing content such as a movie, or convert a general television broadcast into a stereoscopic image and display it on a television screen.

JP 2002-123842 A

However, in the conventional method of generating a stereoscopic image from a normal original image, the hue, saturation, or brightness (saturation in Patent Document 1) of each pixel constituting the original image is generally used as it is. Since the pixel depth information is used, for example, the value of the depth information changes greatly at the boundary between the person who is the subject and the background, and there is a problem that the depth is discontinuous (discontinuous).

When such a discontinuity in depth occurs, only the perspective between the person and the background is emphasized, and the person can be perceived as a flat surface. It becomes. In addition, when changing the position of each pixel in the right-eye image and the left-eye image, the movement amount of the pixel included in the person and the pixel included in the background is greatly different. A large gap (deficiency) will occur in the background.

In the conventional method, in order to avoid such a gap, there is a method in which a blurring process for a boundary portion or a process for enlarging or deforming a person or the like or a background image is performed. In addition to degrading the image quality of the stereoscopic image, the viewer may feel uncomfortable. In addition, these blur processing and enlargement / deformation processing have a problem of increasing the workload of an operator who processes a stereoscopic image on software. Therefore, when generating a stereoscopic image from an original image of a multi-view type or a multi-view parallax type stereoscopic image, there is a problem that an operator's processing work becomes enormous.

In view of such circumstances, the present invention intends to provide a stereoscopic image generation method and a stereoscopic image generation system capable of generating a stereoscopic image from an original image that allows a viewer to perceive a natural stereoscopic effect. It is.

The present invention that achieves the above object includes a feature information acquisition step of acquiring feature information of each pixel constituting an original image, a depth information generation step of generating depth information for each pixel based on the feature information, A stereoscopic image generation step of generating a stereoscopic image in which the position of each pixel is changed based on depth information, and the depth information generation step is performed between the pair of pixels extracted from the original image. An edge setting step for setting an edge on the edge, a weight information setting step for setting weight information on the edge based on the feature information, a start pixel selection step for selecting a start pixel from the pixels, and the start pixel A route information setting step for calculating a route for the weight information from each pixel to each pixel, and setting route information for each pixel; It characterized by having a a depth determination step of setting the depth information on each pixel on the basis of the road information, a stereoscopic image generation method.

In the stereoscopic image generation method that achieves the above object, in the start pixel selection step of the invention, the pixel that is included in the region indicating the innermost part or the region indicating the frontmost part in the original image is selected as the start pixel. It is characterized by doing.

In the stereoscopic image generation method that achieves the above object, the start pixel selection step of the invention is characterized in that a plurality of the start pixels are selected.

In the stereoscopic image generation method that achieves the above object, in the route information setting step of the invention, the route is calculated for each of the plurality of start pixels, a plurality of the route information is set for each pixel, and the depth is set. In the determination step, the depth information is selected based on the plurality of route information depending on whether one of the plurality of route information set for each pixel is selected or the plurality of route information is combined. Is set.

In the stereoscopic image generation method that achieves the above object, in the start pixel selection step of the invention, a plurality of the pixels included in a predetermined region in the original image are collectively selected as one start pixel. Features.

In the stereoscopic image generating method that achieves the above object, the invention further includes a region dividing step of dividing the original image into a plurality of regions, and in the start pixel selecting step, the start pixel is set for each of the plurality of regions. In the path information setting step, the path is calculated for each of the plurality of areas, and the path information is set for each pixel.

In the stereoscopic image generation method that achieves the above object, in the region segmentation step of the invention, the original image is segmented into the plurality of regions for each subject included in the original image.

The present invention that achieves the above object comprises a feature information acquisition means configured by an electronic computer for acquiring feature information of each pixel constituting an original image, and a depth for generating depth information for each pixel based on the feature information. Information generating means, and stereoscopic image generating means for generating a stereoscopic image in which the position of each pixel is changed based on the depth information, wherein the depth information generating means is extracted from the original image Edge setting means for setting an edge between a pair of the pixels, weight information setting means for setting weight information for the edge based on the feature information, and start pixel selection for selecting a start pixel from the pixels Means, route information setting means for calculating a route for the weight information from the start pixel to each pixel, and setting route information for each pixel, and the route It characterized by having a a depth determination means for setting the depth information on each pixel based on broadcast, a stereoscopic image generation system.

According to the present invention, it is possible to achieve an excellent effect that a stereoscopic image that allows a viewer to perceive a natural stereoscopic effect can be generated substantially automatically from an original image.

It is a block diagram which shows the hardware constitutions of the stereoscopic vision image generation system which concerns on 1st Embodiment of this invention. It is a block diagram which shows the program structure and functional structure of the stereoscopic vision image generation system. It is a block diagram which shows the flow of the stereoscopic image generation by the same stereoscopic image generation system. It is a figure which shows the production | generation concept of the depth map in the same stereoscopic vision image generation system. It is a figure which shows the example which calculates the shortest path information in the same stereoscopic vision image generation system. It is a flowchart which shows the stereoscopic vision image generation procedure by the stereoscopic vision image generation system. They are (A) original image and (B) depth map image which show the generation example of the depth map by the same stereoscopic vision image generation system. It is a block diagram which shows the function structure of the stereoscopic vision image generation system which concerns on 2nd Embodiment of this invention. It is a block diagram which shows the flow of the stereoscopic image generation by the same stereoscopic image generation system. It is a block diagram which shows the flow of the stereoscopic vision image generation by the other example of the same stereoscopic vision image generation system. It is a block diagram which shows the flow of the stereoscopic vision image generation by the other example of the same stereoscopic vision image generation system. It is a block diagram which shows the function structure which concerns on the other example of the same stereoscopic vision image generation system. It is a block diagram which shows the flow of the stereoscopic vision image generation by the other example of the same stereoscopic vision image generation system.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

FIG. 1 shows an internal configuration of a computer 10 constituting the stereoscopic image generation system 1 according to the first embodiment. The computer 10 includes a CPU 12, a first storage medium 14, a second storage medium 16, a third storage medium 18, an input device 20, a display device 22, an input / output interface 24, and a bus 26. The CPU 12 is a so-called central processing unit, and executes various programs to realize various functions of the stereoscopic image generation system 1. The first storage medium 14 is a so-called RAM (Random Access Memory) and is a memory used as a work area of the CPU 12. The second storage medium 16 is a so-called ROM (Read Only Memory) and is a memory for storing a basic program executed by the CPU 12. The third storage medium 18 is composed of a hard disk device incorporating a magnetic disk, a disk device accommodating a CD, DVD, or BD, a non-volatile semiconductor flash memory device, and the like. OS (operating system) program that realizes basic operations, a stereoscopic image generation program executed by the CPU 12 when generating a stereoscopic image, a depth map and a stereoscopic image used in this stereoscopic image generation program Various data such as are stored. The input device 20 is a keyboard or a mouse, and is a device for appropriately inputting information to the stereoscopic image generation system 1 by an operator. The display device 22 is a display and provides a visual interface to the worker. The input / output interface 24 is an interface for inputting original image data necessary for the stereoscopic image generation program, and for outputting a depth map and a stereoscopic image generated by the stereoscopic image generation program to the outside. is there. The bus 26 is a wiring for integrally connecting the CPU 12, the first storage medium 14, the second storage medium 16, the third storage medium 18, the input device 20, the display device 22, the input / output interface 24, and the like for communication. It becomes.

In FIG. 2, the program configuration of the stereoscopic image generation program stored in the third storage medium 18 and the stereoscopic image generation system 1 realized by executing the stereoscopic image generation program by the CPU 12. The functional configuration realized by is shown. 3 to 5 conceptually show a stereoscopic image generation method executed by the stereoscopic image generation system 1. FIG. In this stereoscopic image generation system 1, since the configuration of the stereoscopic image generation program and the functional configuration thereof are in a correspondence relationship, the functional configuration of the stereoscopic image generation system 1 will be described here to explain the program. Description is omitted.

The stereoscopic image generation system 1 includes a feature information acquisition unit 140 realized by a feature information acquisition program, a depth information generation unit 160 realized by a depth information generation program, and a stereoscopic image generation realized by a stereoscopic image generation program. A portion 180 is provided.

The feature information acquisition unit 140 acquires feature information 240 of each pixel 204 constituting the original image 200. This feature information 240 includes, for example, characteristic information that each pixel 204 has independently such as the hue, brightness, saturation, and color space of each pixel 204, and pixels around the target pixel 204. 204. Characteristic information derived from the relationship of 204, or in the case of a moving image having a plurality of frames, characteristic information derived from temporal changes of each pixel 204 (relationship with pixels at the same position in the previous and subsequent frames), etc. It is also possible to use.

The depth information generation unit 160 generates a depth map 260 in which the depth information 270 is set in each pixel 204 based on the feature information 240 acquired in each pixel 204.

Specifically, the depth information generation unit 160 includes an edge setting unit 162, a weight information setting unit 164, a start pixel selection unit 166, a path information setting unit 168, and a depth determination unit 170 in more detail.

4, the edge setting unit 162 sets an edge 262 between a pair of pixels 204 extracted from the original image 200. The edge 262 conceptually means a line connecting a pair of pixels 204 or a path connecting both. Considering the graph theory, the pair of pixels 204 are nodes or vertices, and the edges 262 are branches or edges. In the present embodiment, for each pixel 204, an edge 262 for a total of four pixels 204 adjacent in the vertical and horizontal directions is set. Note that the present invention is not limited to the case where the edge 262 is set for each pixel 204 that is vertically and horizontally adjacent to each other, but the diagonally upper right, the upper left, the lower right, and the lower left. An edge 262 can be set for adjacent pixels 204, or an edge 262 can be set for a total of eight pixels 204 obtained by combining these with upper, lower, left and right. In addition, the edge 262 is not necessarily set between adjacent pixels 204, and the edge 262 with respect to a pair of pixels 204 having a certain distance by skipping pixels in the middle, that is, the pixels 204 that have been thinned out. Can also be set. Needless to say, an edge 262 can be set between a pair of pixels 204 located far away like an enclave.

The weight information setting unit 164 sets the weight information 264 for the edge 262 based on a pair of feature information 240 connecting the edges 262. In this embodiment, the weight information 264 uses the difference between the feature information 240 of the pair of pixels 204 connecting the edges 262. The weight information 264 increases as the difference increases, and the weight information 264 decreases as the difference decreases. The weight information 264 is not limited to the “difference” between the pair of feature information 240 at both ends of the edge 262, and various functions that calculate weight information using the pair of feature information 240 are used. Thus, the weight information 264 can be set.

The start pixel selection unit 166 selects a start pixel 266 from each pixel 204 in the original image 200. The start pixel 266 becomes a start point when setting the shortest path information 268 described later. The start pixel 266 can be freely selected from the image 200. For example, as shown in FIG. 3, a group of pixels existing in a region 200A located on the innermost side in the original image 200. Alternatively, it is preferable to select from the pixel group existing in the region 200B located at the foremost side. Although details will be described in detail in the second embodiment, it is also possible to select a plurality of start pixels 266 from the original image 200. Furthermore, as shown in FIG. 3, all the pixels 204 included in the predetermined region 200 </ b> C in the original image 200 can be collectively selected as one start pixel 266.

In this embodiment, one pixel is selected as the start pixel 266 from the innermost region 200A in the original image 200.

The path information setting unit 168 calculates the shortest path using the weight information 264 of the path (edge 262) from the start pixel 266 to each pixel 204 in the original image 200, and sends the shortest path to each of these pixels 204. Information 268 is set. A specific example of this will be described with reference to FIG.

In order to simplify the explanation, it is assumed here that the original image 200 is composed of nine pixels 204A to 204I of 3 rows × 3 columns, and the upper left pixel 204A is the pixel located on the farthest side. Therefore, a case where the pixel is set as the start pixel 266 will be considered. The twelve edges 262 (1) to 262 (12) connecting the pixels 204A to 204I use 1 to 10 by using the relative difference of characteristic information (not shown) held by the pixels 204A to 204I. The weight information 264 is preset. Here, considering the path of the pixel 204D in the upper center stage, as the path connecting the start pixel 204A and the pixel 204D, for example, the first path R1 including only the edge 262 (3) directly connecting the start pixel 204A and the pixel 204D, and the start pixel A second path R2 including three edges 262 (1), 262 (4), and 262 (6) connecting 204A, pixel 204B, pixel 204E, and pixel 204D is provided. The sum of the weight information 264 of the first route R1 is “1”, and the sum of the weight information 264 of the second route R2 is “10” of 3 + 2 + 5. As described above, the sum of the weight information 264 is calculated in the same manner for all possible paths between the start pixel 204A and the pixel 204D, and the shortest path is the smallest value. Here, the first route R1 is the shortest route. As a result, “1”, which is the sum of the weight information 264 on the shortest route, is set as the shortest route information 268 in the pixel 204D.

The route information setting unit 168 sets the shortest route information 268 for all the pixels 204A to 204I by the above method. As a result, the pixel 204A is “0”, the pixel 204B is “3”, the pixel 204C is “11”, the pixel 204D is “1”, the pixel 204E is “5”, the pixel 204F is “10”, and the pixel 204G is “5”. ", The shortest path information 268 of" 12 "is set for the pixel 204H and" 12 "is set for the pixel 204I.

The depth determination unit 170 sets the depth information 270 for each pixel 204 based on the shortest path information 268. In the present embodiment, the depth determination unit 170 uses the shortest path information 268 as the depth information 270 as it is. A depth map 260 is a visual map of the depth information 270 set for each pixel 204.

A value obtained by correcting the shortest path information 268 as needed can be used as the depth information 270. For example, different correction functions are prepared depending on whether the original image 200 is an image of an outdoor landscape or an image of an indoor space. The depth information 270 can also be calculated by applying a correction function selected according to the content.

The stereoscopic image generation unit 180 generates a stereoscopic image 280 composed of the right-eye image 280A and the left-eye image 280B in which the position of each pixel 204 is changed based on the depth map 260. Specifically, the depth information 270 of the depth map 260 is used to reduce the horizontal displacement (shift amount) for the pixels 204 located on the far side and the horizontal direction for the pixels 204 located on the near side. The right eye image 280A and the left eye image 280B including the parallax are generated. As a result, the image 280A for the right eye is shown on the right eye of the viewer (viewer) of the image and the image 280B for the left eye is shown on the left eye, so that the parallax included in the image is processed in the brain. Perceive a feeling.

Next, a procedure for generating a stereoscopic image by the stereoscopic image generating system 1 will be described with reference to FIG.

First, in step 300, a moving image composed of a plurality of original images (frames) 200 is registered in the third storage medium 18 via the input / output interface 24 of the stereoscopic image generation system 1. After that, in step 302, the feature information processing unit 140 extracts the first original image (frame) 200 from the moving image, and acquires the feature information 240 of each pixel 204 constituting this (feature information acquisition step). .

Next, in step 310, a depth map 260 in which depth information 270 is set for each pixel 204 is generated based on the feature information 240 (depth information generation step). The depth information generation step 310 is divided into steps 312 to 320 in detail.

First, in step 312, an edge 262 is set between two approaching pixels 204 (edge setting step). Thereafter, in step 314, weight information 264 is set for the edge 262 based on the feature information 240 already set for each pixel 204 (weight information setting step). Next, in step 316, the start pixel 266 is selected from each pixel 204 (start pixel selection step), and the process proceeds to step 318, where the weight information 264 on the path from the start pixel 266 to each pixel 204 is changed. The shortest path that minimizes the cumulative value is calculated, and the shortest path information 268 that is the minimum cumulative value of the weight information 264 is set for each pixel 204 for which the shortest path is calculated (path information setting step). . Thereafter, in step 320, depth information 270 is set for each pixel 204 using the shortest path information 268, and the depth information 270 is aggregated to generate a depth map 260 for the pixel group (depth determination step).

When the above depth information generation step 310 is completed, the process proceeds to step 330 and the right eye image 280A and the left eye in which the position of each pixel 204 is shifted based on the determined depth information 270 (depth map 260). A stereoscopic image composed of the work image 280B is generated (stereoscopic image generation step).

In addition, although the case where the depth information 270 is aggregated to generate the depth map 260 and the stereoscopic image 280 is generated using the depth map 260 is illustrated here, the present invention is not limited to this. It is possible to generate the stereoscopic image 280 by using the depth information 270 as it is without making a depth map. Further, it is not necessary to wait for the stereoscopic image generation step 330 until all the depth information 270 is generated in units of the original image 200, and the depth information 270 set in units of the pixels 204 is sequentially added to the stereoscopic image generation step 330. It is also possible to sequentially generate a stereoscopic image 280 for each pixel 204 unit. Of course, as shown in this embodiment, it is also preferable that the depth information 270 is imaged or visualized by the depth map 260 as necessary, and the operator of the stereoscopic image generation system 1 visually determines the setting state of the depth information 270. It is convenient when checking.

When the generation of the stereoscopic image 280 from the original image 200 is completed, the process proceeds to step 340, where it is determined whether or not the current original image 200 is the last frame in the moving image. Returning to 302, the next original image (frame) 200 is extracted, and the same steps as described above are repeated. On the other hand, when the original image 200 that generated the stereoscopic image 280 is the last frame in the moving image, the stereoscopic image generation procedure is terminated.

As described above, according to the stereoscopic image generation system 1 of the present embodiment, the depth information 270 that is the basis of the stereoscopic effect when generating the stereoscopic image 280 is used as the weight information 264 along the shortest path between the plurality of pixels 204. It is generated using the shortest path information 268 calculated from the accumulated value of. As a result, the depth information 270 can be made continuous with respect to the set of pixels 204 connected by the edge 262. A natural depth feeling is given to the stereoscopic image 280 generated using the depth information 270. In particular, it is possible to suppress a discontinuity (discontinuity) phenomenon in a stereoscopic image that occurs due to an extreme change in depth information at the boundary between a person on the front side and a background on the back side. The stereoscopic image 280 can be imparted with a stereoscopic effect with little discomfort for the user. Further, with the suppression of this disconnection phenomenon, it is possible to suppress the occurrence of a gap in the generated stereoscopic image 280, and image correction (blurring and image deformation) for filling the gap is also reduced. Deterioration of image quality is suppressed.

Further, in the stereoscopic image generation system 1, the start pixel 266 is selected from the area 200A indicating the innermost part or the area 200B indicating the foremost part in the original image 200. The start pixel 266 serves as a reference point (zero point) when calculating the shortest path information 268 of the other pixels 204. By selecting the start pixel 266 from the backmost or frontmost pixel 204, it is possible to generate the depth map 260 without any sense of incongruity. The selection of the start pixel 266 causes the display device (display) 22 to display the original image 200 and prompts the operator of the stereoscopic image generation system 1 to select the start pixel 266 considered to be the farthest or foremost. You may do it. In addition, the stereoscopic image generation system 1 may analyze the original image 200 to estimate the

regions

200A and 200B that will be the farthest or the foremost, and automatically select the start pixel 266 from the

regions

200A and 200B. .

As a result, since all the depth information 270 can be calculated almost automatically, the work burden on the operator of the stereoscopic image generation system 1 is greatly reduced. In the conventional system, the depth map is selected by selecting an optimal template from a plurality of templates corresponding to assumed typical scenes (mountainous area, sea, room, street, etc.) while checking the stereoscopic image. Complicated work such as adding correction to 260 is required.

In the first embodiment, the case where one pixel is selected as the start pixel 266 in the start pixel selection step 316 is illustrated, but the present invention is not limited to this. For example, as illustrated in FIG. 3, a plurality of pixels 204 included in a predetermined region 200 </ b> C in the original image 200 can be selected as one start pixel 266. In other words, considering the shortest path method, it means that the edge weight information and the shortest path information of all the pixels 204 included in these areas are set to zero or a fixed value (reference value) in advance. By doing in this way, even if it is a case where the image-like noise is contained in this area | region, it becomes possible to cut the influence of noise. Further, since it is possible to omit the calculation of an area where there is no need to make a difference in the sense of depth, such as a clear sky with no clouds, the information processing time for calculating the shortest path can be greatly reduced. In addition, here, only the case where the start pixel 266 is designated in a certain region is shown, but other pixels other than the start pixel can be integrated as a certain region. For example, this region setting is suitable for a simple subject that may share depth information of a certain area range composed of a plurality of adjacent pixels. In this case, in the area to be integrated, the operator gives an area instruction so that these pixel groups are virtually regarded as one pixel. As a result, the information processing time for calculating the shortest path can be greatly reduced.

Result of generating depth map 260 for the purpose of calculating depth information 270 using the original image 200 that is a still image using the stereoscopic image generating system 1 of the present embodiment and visualizing this depth information 270 Is shown in FIG. The original image 200 in FIG. 7A is a scene in which a woman stands in a square with a blue sky and trees on both sides. The start pixel 266 was selected from one pixel in the blue sky region which is the innermost side. In the depth map 260 of FIG. 7B, the minimum value of the depth information 270 (“0” of the start pixel 266 is the minimum value) is shown in black, and the maximum value of the depth information 270 is shown in white. It was expressed visually with a scale image. The depth map 260 generated by the stereoscopic image generating system 1 is expressed in black around the distant blue sky, and the trees lined on both sides are expressed in gray on the back side and white on the near side. Yes. Also, it can be seen that the woman in the center is expressed such that the contour portion is gray and the center portion is close to white, and a delicate sense of depth including the three-dimensional effect of the woman is expressed. In addition, it can be seen that an extremely large difference in gray scale does not occur even at the boundary between the blue sky and the female head, which originally has a large distance difference. As a result, it can be seen that the discontinuity (discontinuity) phenomenon in the stereoscopic image caused by the extreme change in the depth information is suppressed as in the conventional case. Further, as can be seen by comparing the original image 200 and the depth map 260, it can also be seen that the gray scale shading and the actual perspective are expressed very accurately.

Next, a stereoscopic image generation system 401 according to the second embodiment of the present invention will be described with reference to FIG. In addition, about the part which is the same as or similar to the stereoscopic image generation system of 1st Embodiment, description here is abbreviate | omitted by making a name and code | symbol correspond, and it demonstrates centering on a different part.

The stereoscopic image generation system 401 is configured to include a region classification unit 110 realized by a region classification program in addition to the feature information acquisition unit 140, the depth information generation unit 160, and the stereoscopic image generation unit 180.

The area dividing unit 110 divides the original image 200 into a plurality of areas 202 as shown in FIG. In addition, the depth information generation unit 160 generates depth information 270 for each pixel 204 based on the feature information 240 individually for each of the plurality of areas 202A to 202E, and generates an individual depth map 265 corresponding to the areas 202A to 202E. Generate. The stereoscopic image generation unit 180 also changes the position of each pixel 204 based on the plurality of individual depth maps 265A to 265E generated for each of the plurality of regions 202A to 202E (right-eye image). 280A and left-eye image 280B) are generated.

In particular, in the present embodiment, the stereoscopic image generation unit 180 includes the depth information synthesis unit 186. The depth information combining unit 186 combines a plurality of individual depth maps 265A to 265E generated for each of the areas 202A to 202E by the depth information generating unit 160, thereby generating one combined depth map 267. As a result, the operator can visually check the overall stereoscopic effect using the combined depth map 267. The stereoscopic image generation unit 180 generates the right-eye image 280A and the left-eye image 280B using the combined depth map 267. As already described, when the operator does not need the combined depth map 267, the depth information combining unit 186 may not be used. In other words, the stereoscopic image generation unit 180 may generate the stereoscopic video 280 by applying the depth information 270 set for each of the regions 202A to 202E in the depth information generation unit 160 to the pixel 204 unit.

More specifically, when the area segmentation unit 110 segments the original image 200 into a plurality of areas 202A to 202E, the start pixel selection unit 166 selects start pixels 266A to 266E for each of the plurality of areas 202A to 202E. As a result, the route information setting unit 168 calculates the shortest route for each of the plurality of regions 266A to 266E, and sets the shortest route information 268 for each pixel 204 in the regions 202A to 202E. In particular, in the second embodiment, the area classification unit 110 divides the subject included in the original image 200 into a plurality of areas 202A to 202E with the main unit as a main unit.

As a result, the depth information 270 can be calculated independently for each of the areas 202A to 202E set in the original image 200. For example, in the original image 200, a partially independent building or person is partially present from a three-dimensional viewpoint, and apparent three-dimensional continuity between the building or person and other regions is present. Is not set, the depth information 270 is uniquely set by dividing the building or the like by the areas 202A to 202E. As a result, when considering the areas 202A to 202E as a unit, the depth information 270 is calculated by the shortest path method from the start pixels 266A to 266E, so that continuous and delicate depth information 270 is obtained in the areas 202A to 202E.

When the start pixels 266A to 266E are set for each of the areas 202A to 202E as described above, the shortest path information 268 of each of the start pixels 266A to 266E is “zero”. Therefore, if this is adopted as the depth information 270 as it is, there is a possibility that the relative depth feeling is shifted between the plurality of individual depth maps 265. Accordingly, it is preferable that the depth determining unit 170 determines the depth information 270 after correcting the shortest path information 268 as a whole for each of the individual depth maps 265A to 265E. For example, as compared with the first individual depth map 265A of the first area 202A on the background side, all the pixels 204 of the second individual depth map 265B of the second area 202B on the front side are constant with respect to the shortest path information 268. After adding the correction value for the front side shift, this is used as the depth information 270. As described above, by correcting the sense of depth in units of the individual depth maps 265A to 265E, a delicate and smooth three-dimensional feeling is produced in the regions 202A to 202E, and a plurality of individual depth maps 265A to 265E are clearly defined. A clear stereoscopic effect can be imparted.

In this embodiment, the original image 200 is divided into a plurality of regions 202A to 202E, and the start pixels 266A to 266E are selected within the range of the regions 202A to 202E. However, the present invention is not limited to this. Not.

For example, as shown in FIG. 10, the start pixel selection unit 166 selects a plurality of start pixels 266A to 266D from the entire original image 200 without depending on whether or not the original image 200 is divided into regions, and the path The information setting unit 168 calculates the shortest path for each of the plurality of start pixels 266A to 266D for all the pixels 204 of the original image 200, and sets a plurality of shortest path information 268A to 268D for each pixel. it can.

The depth determination unit 170 selects any one of the shortest path information 268A to 268D from the plurality of shortest path information 268 set for each pixel 204, and determines the depth information 270. In addition, the depth determining unit 170 can determine the depth information 270 using a plurality of shortest path information 268A to 268D set for each pixel 204. The determination of selecting one shortest path information from the plurality of shortest path information 268A to 268D or using the plurality of shortest path information 268A to 268D may be performed on the entire original image 200, or the pixel 204 It may be done in units. In the case where the pixel 204 is divided into a plurality of regions, it is also preferable to perform the processing in units of the regions.

This method will be described from another viewpoint with reference to FIG. The depth information generation unit 160 generates a plurality of temporary depth maps 263A to 263D corresponding to the start pixels 266A to 266D. The depth determination unit 170 uses one of the plurality of temporary depth maps 263A to 263D generated in units of the start pixel 266, or overlaps any one of the temporary depth maps 263A to 263D. It is determined whether or not. At this time, if the original image 200 is divided into a plurality of areas 202A to 202D, individual depth maps 265A to 265D corresponding to the areas 202A to 202D are generated if the determination is made in units of the areas 202A to 202D. The individual depth maps 265A to 265D are combined to obtain a combined depth map 267.

As described above, the options for determining the depth information 270 can be increased. This option means the start pixels 266A to 266D in this embodiment. In particular, here, the start pixels 266A to 266D are selected from a wide range including outside the range of the regions 202A to 202D. For example, in the first region 202A located on the left side of the original image 200, the shortest path information 268A (provisional depth map 263A) calculated based on the start pixel 266A at the right end of the original image 200 can be applied. In the second region 202B located on the right side of the original image 200, the shortest path information 268B (provisional depth map 263B) calculated based on the start pixel 266B at the left end of the original image 200 can be applied. Further, for example, in the third region 202C located on the near side of the original image 200, the shortest path information 268C (temporary depth map 263C) calculated based on the start pixel 266C on the back side of the original image 200 can be applied. Further, in the fourth region 202D located on the back side of the original image 200, the shortest path information 268D (temporary depth map 263D) calculated based on the start pixel 266D on the near side of the original image 200 can be applied.

As already described, for example, a plurality of the shortest path information 268A to 268D (temporary depth maps 263A to 263D) are selected, and the depth information 270 (joint depth map 267) can be determined using these. preferable. In this way, each of the shortest path information 268A to 268D (provisional depth maps 263A to 263D) includes other shortest path information 268A to 268D (provisional) even if it contains an error portion for which accurate depth information cannot be obtained. If accurate depth information is obtained in the depth maps 263A to 263D), the error information can be automatically compensated for by using together, and smoother depth information 270 (joint depth map 267) can be obtained. ) Can be obtained. When the depth information 270 is determined using a plurality of shortest path information 268A to 268D, various calculation methods such as a sum total and an average value thereof can be applied.

In the second embodiment described above, a case where the combined depth map 267 is generated by combining the individual depth maps 265 and then the stereoscopic image 280 (the right-eye image 280A and the left-eye image 280B) is generated is illustrated. However, the present invention is not limited to this. For example, like the stereoscopic image generation system 501 shown in FIGS. 12 and 13, the stereoscopic image generation unit 180 includes an individual image generation unit 182 and a stereoscopic image synthesis unit 184. The individual image generation unit 182 generates individual stereoscopic images 282A to 282D (right-eye individual images and left-eye individual images) in which the pixel positions are changed based on the individual depth maps 265A to 265D for each of the regions 202A to 202D. To generate. By applying the generation of the individual stereoscopic images 282A to 282D to all the original images 200 (all frames in the moving image), the operator confirms the completion of the individual stereoscopic images 282A to 282D in units of the areas 202A to 202D. To do. Thereafter, the stereoscopic image combining unit 184 combines the individual stereoscopic images 282A to 282D to generate a stereoscopic image 280 (right eye image 280A and left eye image 280B).

The generation time of the individual stereoscopic images 282A to 282D by the stereoscopic image generation system 501 can be significantly shortened compared to the time for generating the entire stereoscopic image 280. Therefore, the operator can proceed with the work while efficiently checking the stereoscopic effect in units of the areas 202A to 202D. That is, after adjusting and confirming the stereoscopic effect in units of the areas 202A to 202D in detail to enhance the completeness of the individual stereoscopic images 282A to 282D, the individual stereoscopic images 282A to 282D are synthesized to obtain the final stereoscopic image. Since the visual image 280 (the right-eye image 280A and the left-eye image 280B) is generated, the stereoscopic image 280 with less discomfort can be obtained.

As described above, according to the second embodiment, since a plurality of start pixels 266 that are reference values for calculating a sense of depth are selected, these can be used in any combination so that they can be used in accordance with the scene of the original image 200. The depth information 270 can be determined flexibly. In particular, since the original image 200 is divided into a plurality of areas 202A to 202D and the optimum start pixels 266A to 266D are selected for the areas 202A to 202D, it is possible to produce a more natural stereoscopic effect. Become.

In the above-described embodiment, the case where the shortest path in which the cumulative value of the weight information 264 on the path from the start pixel 266 to each pixel 204 is minimized is illustrated in the path information setting step 318. The invention is not limited to this. For example, by using a prim method or the like, a route that has a minimum sum of weights of a set of sides may be obtained from routes constituted by a subset of sides including all pixels 204. In other words, in the present invention, any algorithm can be used as long as any weight value can be specified using various paths between pixels.

In the above embodiment, the binocular parallax stereoscopic image of the right eye image and the left eye image is exemplified, but the present invention is not limited to this. For example, this depth information may be used to generate a multi-view stereoscopic image, and it is also possible to generate a multi-view parallax stereoscopic image. That is, in the present invention, any type of stereoscopic video using depth information may be used.

The stereoscopic image generation method and the stereoscopic image generation system of the present invention can be applied to various devices such as a television and a game machine that convert a normal image into a stereoscopic image and display it in addition to the field of production of movies and television programs. Can be used in the field.

Claims

A feature information acquisition step of acquiring feature information of each pixel constituting the original image;
A depth information generating step for generating depth information for each pixel based on the feature information;
A stereoscopic image generation step of generating a stereoscopic image in which the position of each pixel is changed based on the depth information,
The depth information generation step includes:
An edge setting step for setting an edge between a pair of the pixels extracted from the original image;
A weight information setting step for setting weight information for the edge based on the feature information;
A start pixel selection step of selecting a start pixel from the pixels;
A path information setting step for calculating a path for the weight information from the start pixel to each pixel and setting path information for each pixel;
A depth determination step for setting the depth information for each pixel based on the path information.
Stereoscopic image generation method.
In the start pixel selecting step, the pixel included in the region indicating the innermost part or the region indicating the frontmost part in the original image is selected as the start pixel.
The stereoscopic image generation method according to claim 1.
In the start pixel selection step, a plurality of the start pixels are selected.
The stereoscopic image generation method according to claim 1 or 2.
In the path information setting step, the path is calculated for each of the plurality of start pixels, and a plurality of path information is set for each pixel.
In the depth determination step, based on the plurality of route information, depending on whether one of the plurality of route information set for each pixel is selected or the plurality of route information is combined. It is characterized by setting depth information.
The stereoscopic image generation method according to claim 3.
In the start pixel selection step, the plurality of pixels included in a predetermined region in the original image are collectively selected as one start pixel,
The stereoscopic image generation method according to any one of claims 1 to 4.
A region dividing step of dividing the original image into a plurality of regions;
In the start pixel selection step, the start pixel is selected for each of the plurality of regions,
In the route information setting step, the route is calculated for each of the plurality of regions, and the route information is set in each pixel,
The stereoscopic image generation method according to any one of claims 1 to 5.
In the area dividing step, the original image is divided into the plurality of areas for each subject included in the original image,
The stereoscopic image generation method according to claim 6.
Composed by an electronic computer,
Feature information acquisition means for acquiring feature information of each pixel constituting the original image;
Depth information generating means for generating depth information for each pixel based on the feature information;
Stereoscopic image generation means for generating a stereoscopic image in which the position of each pixel is changed based on the depth information;
The depth information generating means includes
Edge setting means for setting an edge between a pair of the pixels extracted from the original image;
Weight information setting means for setting weight information for the edge based on the feature information;
Start pixel selection means for selecting a start pixel from the pixels;
Path information setting means for calculating a path for the weight information from the start pixel to each pixel, and setting path information for each pixel;
Depth determining means for setting the depth information for each pixel based on the path information,
Stereoscopic image generation system.