WO2019218887A1 - 二维图像转换成三维图像的方法、装置及三维成像系统 - Google Patents
二维图像转换成三维图像的方法、装置及三维成像系统 Download PDFInfo
- Publication number
- WO2019218887A1 WO2019218887A1 PCT/CN2019/085688 CN2019085688W WO2019218887A1 WO 2019218887 A1 WO2019218887 A1 WO 2019218887A1 CN 2019085688 W CN2019085688 W CN 2019085688W WO 2019218887 A1 WO2019218887 A1 WO 2019218887A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- dimensional image
- dimensional
- eye image
- processed
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000003384 imaging method Methods 0.000 title claims abstract description 22
- 230000009466 transformation Effects 0.000 claims abstract description 54
- 238000012545 processing Methods 0.000 claims description 24
- 230000015654 memory Effects 0.000 claims description 19
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 6
- 230000002194 synthesizing effect Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 15
- 230000010287 polarization Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000003278 mimic effect Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 210000001525 retina Anatomy 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/10—Processing, recording or transmission of stereoscopic or multi-view image signals
- H04N13/106—Processing image signals
- H04N13/128—Adjusting depth or disparity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/265—Mixing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/10—Geometric effects
- G06T15/20—Perspective computation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/14—Transformations for image registration, e.g. adjusting or mapping for alignment of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/20—Linear translation of whole images or parts thereof, e.g. panning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/10—Processing, recording or transmission of stereoscopic or multi-view image signals
- H04N13/106—Processing image signals
- H04N13/156—Mixing image signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/261—Image signal generators with monoscopic-to-stereoscopic image conversion
Definitions
- the present invention relates to the field of image processing technologies, and in particular, to a method, an apparatus, and a three-dimensional imaging system for converting a two-dimensional image into a three-dimensional image.
- Stereoscopic vision that is, binocular vision, subjectively produces a sense of the thickness of the object being viewed and the depth or distance of the space.
- the main reason is that the image of the same object on the retina of the two eyes is not exactly the same, the left eye sees more of the left side of the object from the left, while the right eye sees the right side of the object from the right. More; image information from both eyes is processed by the visual high-level center to produce an image of a stereoscopic object.
- 3D three-dimensional
- Most of the existing 3D cameras are structures that mimic the human eye. They are composed of dual cameras.
- the image captured by one camera corresponds to the left eye image of the human eye
- the image captured by the other camera corresponds to the right eye image of the human eye.
- the processing device synthesizes the left eye image and the right eye image to form a 3D image.
- the embodiments of the present invention provide a method, a device, and an image processing device for converting a two-dimensional image into a three-dimensional image, so as to solve the problem that the 3D imaging effect is not good.
- an embodiment of the present invention provides a method for converting a two-dimensional image into a three-dimensional image, including:
- the left eye image and the right eye image after the distance adjustment are combined.
- a two-dimensional image is processed to perform a perspective transformation to create a binocular parallax image to realize stereo vision; and the left-eye image and the right-eye image undergoing perspective transformation are adjusted in distance to form binocular parallax, and a convergence angle is created.
- the images observed by the naked eye are located at different depths, so that different stereoscopic effects can be seen. That is, by performing image transformation on a two-dimensional image, the resolution and sharpness of the image are not involved, and thus the image quality of the 3D imaged image is the same as that of the original two-dimensional image, and does not affect the effect of 3D imaging.
- the performing the perspective transformation on the two-dimensional image to be processed includes:
- Embodiments of the present invention convert a two-dimensional image into two images corresponding to left and right eyes by linear scaling, that is, convert a non-parallax 2D image into a left eye image and a right eye image having parallax, the conversion process involving only images
- the size is independent of the image quality, so the left eye image and the right eye image formed by linear scaling are of the same quality as the original two-dimensional image.
- the conversion method provided by the embodiment of the invention can form a left eye image and a right eye image under the premise of ensuring the image quality is unchanged.
- the linear scaling of the sizes of the sides according to the preset rule includes:
- the linear scaling is performed on the images of each line in turn.
- a progressive scan is performed by processing a two-dimensional image, that is, linearly scaling each row in turn, thereby reducing the amount of processed data, and real-time conversion of the two-dimensional image can be realized.
- the adjusting the distance between the left eye image and the right eye image according to the result of the perspective transformation comprises:
- Embodiments of the present invention form a left-eye image and a right-eye image by using the same image template, and translate the left-eye image and the right-eye image to create binocular parallax and convergence angle, thereby improving conversion efficiency.
- the two-dimensional image to be processed is a frame image in the video stream.
- the method for converting a two-dimensional image into a three-dimensional image provided by the embodiment of the invention can convert one frame of image in the video stream and a single two-dimensional image, and has wide application.
- an embodiment of the present invention provides an apparatus for converting a two-dimensional image into a three-dimensional image, including:
- a perspective transformation module configured to perform perspective transformation on the two-dimensional image to be processed, to obtain a left-eye image and a right-eye image, respectively, wherein the perspective transformation is to map the to-be-processed two-dimensional image according to a preset rule;
- An adjustment module configured to adjust a distance between the left eye image and the right eye image according to a result of the perspective transformation
- a synthesis module for synthesizing the left eye image and the right eye image after the distance adjustment.
- a two-dimensional image is processed to perform a perspective transformation to create a binocular parallax image to realize stereo vision; and the left-eye image and the right-eye image undergoing perspective transformation are adjusted in distance to form binocular parallax, and a convergence angle is created.
- the images observed by the naked eye are located at different depths, so that different stereoscopic effects can be seen. That is, by performing image transformation on a two-dimensional image, the resolution and sharpness of the image are not involved, and thus the image quality of the 3D imaged image is the same as that of the original two-dimensional image, and does not affect the effect of 3D imaging.
- the perspective transformation module includes:
- An extracting unit configured to align the two-dimensional image to be processed onto an image template, and extract a size of the two-dimensional image to be processed
- a linear scaling unit configured to linearly scale the sizes of the sides according to the preset rule to obtain a first image
- a mirroring unit configured to mirror the first image to obtain a second image, wherein the first image is the left eye image, and the second image is the right eye image; or, the first The image is the right eye image and the second image is the left eye image.
- an embodiment of the present invention provides an image processing apparatus, including:
- a memory and a processor wherein the memory and the processor are in communication with each other, wherein the memory stores computer instructions, and the processor executes the computer instructions to perform the first aspect of the invention, or A method of converting a two-dimensional image described in any one of the embodiments into a three-dimensional image.
- an embodiment of the present invention provides a computer readable storage medium storing computer instructions for causing the computer to perform the first aspect of the present invention, or
- the two-dimensional image described in any one of the embodiments is converted into a three-dimensional image method.
- an embodiment of the present invention provides a three-dimensional imaging system, including:
- An image acquisition device the lens for acquiring an image is composed of a single lens
- the image processing device of the third aspect of the present invention is electrically connected to the image capturing device for converting a two-dimensional image into a three-dimensional image;
- An image display device electrically coupled to the image processing device for displaying the three-dimensional image.
- the three-dimensional imaging system provided by the embodiment of the present invention, wherein the lens of the image capturing device is composed of a single lens, reduces the volume of the entire image capturing device; in addition, the single-lens image capturing device only needs one image acquired by the data line pair
- the transmission can reduce the inner diameter of the connecting line between the image capturing device and the image processing device, so that the three-dimensional imaging system can be applied to a small-sized human body, and three-dimensional imaging of the human body further improves the three-dimensional imaging system. Use range.
- FIG. 1 is a flow chart showing a specific schematic method of a method for converting a two-dimensional image into a three-dimensional image in an embodiment of the present invention
- FIG. 2 is a schematic diagram showing the relationship between the convergence angle and the distance between the left and right eye images in the embodiment of the present invention
- FIG. 3 is a flow chart showing another specific schematic method of a method for converting a two-dimensional image into a three-dimensional image in an embodiment of the present invention
- FIG. 4 is a schematic diagram showing the principle of linear scaling in an embodiment of the present invention.
- FIG. 5 is a flow chart showing another specific schematic method of a method for converting a two-dimensional image into a three-dimensional image in an embodiment of the present invention
- FIG. 6 is a schematic structural diagram of an apparatus for converting a two-dimensional image into a three-dimensional image in an embodiment of the present invention
- FIG. 7 is a schematic diagram showing another specific schematic structure of an apparatus for converting a two-dimensional image into a three-dimensional image in an embodiment of the present invention.
- FIG. 8 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present invention.
- Fig. 9 is a view showing a concrete schematic configuration of a three-dimensional imaging system in an embodiment of the present invention.
- the method for converting a two-dimensional image into a three-dimensional image creates a binocular parallax image, that is, a left eye image and a right eye image, by stereoscopically transforming the two-dimensional image, thereby realizing stereoscopic vision; and further, by adjusting the left eye image and The distance between the images of the right eye creates a convergence angle; using the binocular parallax image, combined with the convergence angle, a 3D image can be formed.
- An embodiment of the present invention provides a method for converting a two-dimensional image into a three-dimensional image. As shown in FIG. 1, the method includes:
- the two-dimensional image to be processed obtained by the device for converting the two-dimensional image into a three-dimensional image may be a two-dimensional image; or may be a frame image in the video stream; or may collect the video in real time, and extract each frame image from it, only It is necessary to ensure that the two-dimensional image is converted into a three-dimensional image to obtain a two-dimensional image to be processed.
- the two-dimensional image to be processed is subjected to perspective transformation to obtain a left eye image and a right eye image, respectively.
- the perspective transformation is to map the two-dimensional image to be processed according to a preset rule.
- the apparatus for converting a two-dimensional image into a three-dimensional image is mapped according to a preset rule to process the two-dimensional image, that is, on the basis of the two-dimensional image to be processed, the left-eye image and the right-eye image are formed by image processing according to the perspective transformation.
- the preset rule is used to represent the method of perspective transformation. For example, the transformed image has a large near end and a far end is small; or a post-perspective image is calculated by a formula.
- the apparatus for converting a two-dimensional image into a three-dimensional image adjusts the distance between the left-eye image and the right-eye image formed after the perspective transformation to create a convergence angle.
- the inventors have found through experiments that when the distance between images changes, the corresponding convergence angle changes.
- FIG. 2 the relationship between the convergence angle and the distance between the left and right eye images is described.
- the convergence angle is ⁇ 1
- the distance between the left and right eyes is small
- the convergence angle is ⁇ 2
- the distance between the left and right eyes is large; that is, as the distance between the left and right eyes changes, the convergence angle also changes accordingly. Therefore, in the present invention, the convergence angle is created by adjusting the distance between the left and right eyes.
- the device for converting a two-dimensional image into a three-dimensional image combines the adjusted left-eye image and the right-eye image, that is, the binocular parallax and the convergence angle created by the image transformation, and the left-eye image and the right eye of the distance adjustment sum
- the image is synthesized and output to the image display device for subsequent three-dimensional image display.
- the subsequent image display device can adjust the polarization directions of the left eye image and the right eye image, so that the polarization directions of the two images are perpendicular to each other, and the user can wear the 3D glasses to view the 3D image when using the device; In the way of adjusting the polarization direction, it is only necessary to ensure that the polarization directions of the two images respectively seen by the two eyes of the person are perpendicular to each other.
- a two-dimensional image is processed to perform a perspective transformation to create a binocular parallax image to realize stereo vision; and the left-eye image and the right-eye image undergoing perspective transformation are adjusted in distance to form binocular parallax, and a convergence angle is created.
- the images observed by the naked eye are located at different depths, so that different stereoscopic effects can be seen. That is, by performing image transformation on a two-dimensional image, the resolution and sharpness of the image are not involved, and thus the image quality of the 3D imaged image is the same as that of the original two-dimensional image, and does not affect the effect of 3D imaging.
- the embodiment of the invention further provides a method for converting a two-dimensional image into a three-dimensional image. As shown in FIG. 3, the method includes:
- the two-dimensional image to be processed is a frame image in the video stream
- the device that converts the two-dimensional image into a three-dimensional image sequentially extracts each frame image from the video stream and uses it as a two-dimensional image to be processed. Therefore, the method provided by this embodiment can convert the video stream collected by the device into 3D video in real time.
- the perspective transformation is to map the two-dimensional image to be processed according to a preset rule.
- the apparatus for converting a two-dimensional image into a three-dimensional image in this embodiment is provided with an image template for normalizing the two-dimensional image to be processed.
- S221 Align the two-dimensional image to be processed onto the image template, and extract the size of the two-dimensional image to be processed.
- the two-dimensional image to be processed is converted into a three-dimensional image
- the two-dimensional image to be processed is aligned onto the image template, and the two-dimensional image to be processed is scaled to ensure that the two-dimensional image to be processed does not exceed The range of image templates.
- the size of the two-dimensional image to be processed is extracted, which is used to represent the size of each side of the two-dimensional image to be processed.
- the principle of linear scaling is as shown in FIG. 4, and the perspective transformation is that the left side of the original image is a rotation axis, the angle is turned to the inside of the screen, and the same angle is rotated to the outside of the screen, which are respectively formed in the middle of FIG. 4 and The rightmost image.
- the size of the two-dimensional image to be processed is linearly scaled so that the scaled left and right eye images reach the effect shown in FIG. Specifically, the following steps may be included:
- the device for converting a two-dimensional image into a three-dimensional image performs a progressive scan on the two-dimensional image to be processed aligned on the image template to obtain the size of each line of the two-dimensional image to be processed.
- the device for converting a two-dimensional image into a three-dimensional image is linearly scaled according to the principle that one end is enlarged and the other end is small, and the size of each line of the two-dimensional image to be processed is linearly scaled to obtain a first image after size scaling.
- By linearly scaling each line in turn, the amount of data processed is reduced, enabling real-time conversion of two-dimensional images.
- the device for converting the two-dimensional image into the three-dimensional image mirrors the first image to obtain a second image; that is, the first image is mirrored in the vertical direction to obtain a second image.
- the first image is a left eye image, and the second image is a right eye image; or the first image is a right eye image, and the second image is a left eye image.
- the two-dimensional image is converted into a three-dimensional image
- the left-eye image and the right-eye image are formed
- the left-eye image and the right-eye image are superimposed, and the distance between the left-eye image and the right-eye image is adjusted, so that the two images are heavy. Shadow.
- the means for converting the two-dimensional image into a three-dimensional image recombines the distance-adjusted left-eye image and the ghost image of the right-eye image for display of the 3D image on the image display device.
- the two-dimensional image is converted into two images corresponding to the left and right eyes by linear scaling, that is, 2D without parallax
- the image is converted into a left-eye image and a right-eye image having parallax, and the conversion process relates only to the image size regardless of the image quality, and thus the left-eye image and the right-eye image formed by linear scaling are of the same quality as the original two-dimensional image.
- the conversion method provided by the embodiment of the invention can form a left eye image and a right eye image under the premise of ensuring the image quality is unchanged.
- the embodiment further provides a method for converting a two-dimensional image into a three-dimensional image. As shown in FIG. 5, the method includes:
- the image template to be processed by the normalized two-dimensional image is used to adjust the distance between the left eye image and the right eye image. Specifically, the following steps are included:
- the device for converting a two-dimensional image into a three-dimensional image simultaneously aligns the left-eye image and the right-eye image onto the image template, that is, the left and right eye images are translated on the basis of the image template, and can ensure the comparison without increasing the amount of data processing. Good translation effect, improve the conversion efficiency of 2D images.
- the first direction is a horizontal direction
- one of the left and right eye images aligned on the image template is translated in the horizontal direction, so that the distance between the left and right eye images reaches a preset distance, or simultaneously moves in the opposite direction.
- the preset distance may be specifically set according to the size of the actual display device.
- the left-eye image and the right-eye image are formed by using the same image template, and the left-eye image and the right-eye image are translated, Create binocular parallax and convergence angle to improve conversion efficiency.
- An embodiment of the present invention further provides a device for converting a two-dimensional image into a three-dimensional image. As shown in FIG. 6, the device includes:
- the obtaining module 41 is configured to acquire a two-dimensional image to be processed.
- the perspective transformation module 42 is configured to perform perspective transformation on the two-dimensional image to be processed to obtain a left-eye image and a right-eye image, respectively, wherein the perspective transformation is to map the two-dimensional image to be processed according to a preset rule.
- the adjusting module 43 is configured to adjust a distance between the left eye image and the right eye image according to the result of the perspective transformation.
- the synthesizing module 44 is configured to synthesize the left eye image and the right eye image after the distance adjustment.
- the apparatus for converting a two-dimensional image provided in the embodiment of the present invention into a three-dimensional image by performing perspective transformation on the two-dimensional image to be processed, creating a binocular parallax image to realize stereoscopic vision; and performing a perspective-transformed left-eye image and a right-eye image
- the distance is adjusted to form a binocular parallax, and a convergence angle is created, so that the images observed by the naked eye are located at different depths, so that different stereoscopic effects can be seen. That is, by performing image transformation on a two-dimensional image, the resolution and sharpness of the image are not involved, and thus the image quality of the 3D imaged image is the same as that of the original two-dimensional image, and does not affect the effect of 3D imaging.
- the perspective transformation module 42 includes:
- the extracting unit 421 is configured to align the two-dimensional image to be processed onto the image template, and extract the size of the two-dimensional image to be processed.
- the linear scaling unit 422 is configured to linearly scale the size according to a preset rule to obtain a first image.
- the mirroring unit 423 is configured to mirror the first image to obtain a second image, wherein the first image is a left eye image and the second image is a right eye image; or the first image is the right eye image, and the second image is For the left eye image.
- An embodiment of the present invention further provides an image processing apparatus.
- the image processing apparatus may include a processor 51 and a memory 52, wherein the processor 51 and the memory 52 may be connected by a bus or other means, in FIG. Take the bus connection as an example.
- the processor 51 can be a Central Processing Unit (CPU).
- the processor 51 can also be another general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or Other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., or a combination of the above various types of chips.
- DSP digital signal processor
- ASIC application specific integrated circuit
- FPGA field-programmable gate array
- Other programmable logic devices discrete gates or transistor logic devices, discrete hardware components, etc., or a combination of the above various types of chips.
- the memory 52 is used as a non-transitory computer readable storage medium for storing a non-transitory software program, a non-transitory computer executable program, and a module, and the method for converting a two-dimensional image into a three-dimensional image in the embodiment of the present invention corresponds to
- the program instructions/modules for example, the first acquisition module 41, the perspective transformation module 42, the adjustment module 43, and the synthesis module 44 shown in FIG. 6).
- the processor 51 executes various functional applications and data processing of the processor by running non-transitory software programs, instructions and modules stored in the memory 52, that is, converting the two-dimensional image in the above method embodiment into a three-dimensional image. method.
- the memory 52 may include a storage program area and an storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created by the processor 51, and the like.
- memory 52 can include high speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device.
- memory 52 may optionally include memory remotely located relative to processor 51, which may be coupled to processor 51 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
- the one or more modules are stored in the memory 52, and when executed by the processor 51, a method of converting a two-dimensional image in the embodiment shown in FIGS. 1, 3, and 5 into a three-dimensional image is performed .
- the embodiment of the present invention further provides a three-dimensional imaging system. As shown in FIG. 9, the system includes an image acquisition device 61, an image processing device 62, and an image display device 63.
- the lens for acquiring an image is composed of a single lens.
- the image processing device 62 is electrically connected to the image acquisition device 61 for converting the two-dimensional image to be processed output by the image acquisition device 61 into a three-dimensional image.
- the image display device 63 is electrically connected to the image processing device 62 for displaying a three-dimensional image output by the image processing device 62.
- the three-dimensional imaging system provided by the embodiment of the present invention, wherein the lens of the image capturing device 61 is composed of a single lens, reduces the volume of the entire image capturing device 61; in addition, the single-lens image capturing device only needs one data line pair acquisition.
- the image is transmitted, and the inner diameter of the connecting line between the image capturing device 61 and the image processing device 62 can be reduced, so that the three-dimensional imaging system can be applied to a small-sized object, such as a human body, to perform three-dimensional imaging of the human body. , further improving the scope of use of the three-dimensional imaging system.
- the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk (Hard Disk). Drive, abbreviated: HDD) or Solid-State Drive (SSD), etc.; the storage medium may also include a combination of the above types of memories.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
- Image Analysis (AREA)
Abstract
本发明公开了一种二维图像转换成三维图像的方法、装置及三维成像系统，其中，方法包括获取待处理二维图像；对待处理二维图像进行透视变换，分别得到左眼图像和右眼图像；根据透视变换的结果，调节左眼图像与右眼图像之间的距离；合成距离调节后的左眼图像以及右眼图像。本发明实施例通过对待处理二维图像进行透视变换，创造出双眼视差图像；并将经过透视变换的左眼图像以及右眼图像进行距离的调节，形成双目视差创建收敛角，使肉眼观察的图像位于不同的深度处，从而可以看到不同的立体效果。通过对二维图像进行图像变换，并不涉及图像的分辨率以及清晰度，进而3D成像的图像与原始的二维图像的图像质量相同，并不影响3D成像的效果。
Description
本发明涉及图像处理技术领域，具体涉及一种二维图像转换成三维图像的方法、装置及三维成像系统。
立体视觉，即双眼视物时，主观上可产生被视物体的厚度以及空间的深度或距离等感觉。其主要原因是，同一被视物体在两眼视网膜上的像并不完全相同，左眼从左方看到物体的左侧面较多，而右眼则从右方看到物体的右侧面较多；来自两眼的图像信息经过视觉高级中枢处理后，产生一个有立体感的物体的形象。
随着显示技术和数字技术的发展，利用电子产品模仿人眼的立体视觉已经成为研究热点。在现有技术中，只有采用三维(3D)摄像头才能使用户看到3D图像。现有的3D摄像头多数是模仿人眼的结构，由双摄像头构成，一个摄像头采集的图像对应于人眼的左眼图像，另一个摄像头采集的图像对应于人眼的右眼图像，再利用图像处理设备合成左眼图像以及右眼图像，即可形成3D图像。
其中，现有技术中在利用3D摄像头采集图像时，一般在在摄像头的镜头前方设置两个偏振方向互相垂直的偏振片，以得到左眼用图像以及右眼用图像。由于每个摄像头仅采集一个偏振方向的图像，会导致整个图像的分辨率，清晰度为实际图像的一半，进而影响3D成像的效果。
发明内容
有鉴于此，本发明实施例提供了一种二维图像转换成三维图像的方法、 装置及图像处理设备，以解决3D成像效果不佳的问题。
根据第一方面，本发明实施例提供了一种二维图像转换成三维图像的方法，包括：
获取待处理二维图像；
对所述待处理二维图像进行透视变换，分别得到左眼图像和右眼图像，其中，所述透视变换为按照预设规则对所述待处理二维图像进行映射；
根据所述透视变换的结果，调节所述左眼图像与所述右眼图像之间的距离；
合成距离调节后的所述左眼图像以及右眼图像。
本发明实施例通过对待处理二维图像进行透视变换，创造出双眼视差图像，实现立体视觉；并将经过透视变换的左眼图像以及右眼图像进行距离的调节，形成双目视差，创建收敛角，使肉眼观察的图像位于不同的深度处，从而可以看到不同的立体效果。即，通过对二维图像进行图像变换，并不涉及图像的分辨率以及清晰度，进而3D成像的图像与原始的二维图像的图像质量相同，并不影响3D成像的效果。
结合第一方面，在第一方面第一实施方式中，所述对所述待处理二维图像进行透视变换，包括：
将所述待处理二维图像对齐到图像模板上，提取所述待处理二维图像的尺寸；
按照所述预设规则依次对各边所述尺寸进行线性缩放，得到第一图像；
镜像处理所述第一图像，得到第二图像；其中，所述第一图像为所述左眼图像，所述第二图像为所述右眼图像；或，所述第一图像为所述右眼 图像，所述第二图像为所述左眼图像。
本发明实施例通过将二维图像通过线性缩放转换为对应于左右眼的两幅图像，即，将无视差的2D图像转换成具有视差的左眼图像与右眼图像，该转换过程仅涉及图像尺寸而与图像质量无关，因此经过线性缩放所形成的左眼图像以及右眼图像与原始二维图像的质量相同。本发明实施例提供的转换方法能够在保证图像质量不变的前提下，形成左眼图像以及右眼图像。
结合第一方面第一实施方式，在第一方面第二实施中，所述按照所述预设规则依次对各边所述尺寸进行线性缩放，包括：
逐行扫描所述待处理二维图像；
依次对每行的图像进行所述线性缩放。
本发明实施例通过对待处理二维图像进行逐行扫描，即依次对每行进行线性缩放，减小了处理的数据量，能够实现二维图像的实时转换。
结合第一方面第一实施方式，在第一方面第三实施方式中，所述根据所述透视变换的结果，调节所述左眼图像与所述右眼图像之间的距离，包括：
将所述左眼图像与所述右眼图像同时对齐到所述图像模板上；
沿第一方向平移所述左眼图像或右眼图像，使得所述左眼图像与所述右眼图像之间的距离达到预设距离。
本发明实施例通过利用同一图像模板形成左眼图像和右眼图像，以及对左眼图像和右眼图像进行平移，创造出双眼视差以及收敛角，使得转换效率的提高。
结合第一方面，在第一方面第四实施方式中，所述待处理二维图像为视频流中的一帧图像。
本发明实施例提供的二维图像转换成三维图像的方法，能够对视频流中的一帧图像，以及，单个二维图像进行转换，具有广泛的应用。
根据第二方面，本发明实施例提供了一种二维图像转换成三维图像的装置，包括：
获取模块，用于获取待处理二维图像；
透视变换模块，用于对所述待处理二维图像进行透视变换，分别得到左眼图像和右眼图像，其中，所述透视变换为按照预设规则对所述待处理二维图像进行映射；
调节模块，用于根据所述透视变换的结果，调节所述左眼图像与所述右眼图像之间的距离；
合成模块，用于合成距离调节后的所述左眼图像以及右眼图像。
本发明实施例通过对待处理二维图像进行透视变换，创造出双眼视差图像，实现立体视觉；并将经过透视变换的左眼图像以及右眼图像进行距离的调节，形成双目视差，创建收敛角，使肉眼观察的图像位于不同的深度处，从而可以看到不同的立体效果。即，通过对二维图像进行图像变换，并不涉及图像的分辨率以及清晰度，进而3D成像的图像与原始的二维图像的图像质量相同，并不影响3D成像的效果。
结合第二方面，在第二方面第一实施方式中，透视变换模块，包括：
提取单元，用于将所述待处理二维图像对齐到图像模板上，提取所述待处理二维图像的尺寸；
线性缩放单元，用于按照所述预设规则依次对各边所述尺寸进行线性缩放，得到第一图像；
镜像单元，用于镜像处理所述第一图像，得到第二图像；其中，所述第一图像为所述左眼图像，所述第二图像为所述右眼图像；或，所述第一图像为所述右眼图像，所述第二图像为所述左眼图像。
根据第三方面，本发明实施例提供了一种图像处理设备，包括：
存储器和处理器，所述存储器和所述处理器之间互相通信连接，所述存储器中存储有计算机指令，所述处理器通过执行所述计算机指令，从而执行本发明第一方面，或第一方面任意一种实施方式中所述的二维图像转换成三维图像的方法。
根据第四方面，本发明实施例提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机指令，所述计算机指令用于使所述计算机执行本发明第一方面，或第一方面任意一种实施方式中所述的二维图像转换成三维图像方法。
根据第五方面，本发明实施例提供了一种三维成像系统，包括：
图像采集设备，采集图像的镜头由单镜头组成；
本发明第三方面中所述的图像处理设备，与所述图像采集设备电连接，用于将二维图像转换成三维图像；
图像显示设备，与所述图像处理设备电连接，用于显示所述三维图像。
本发明实施例提供的三维成像系统，其中，在图像采集设备的镜头由单镜头组成，减小了整个图像采集设备的体积；此外，单镜头的图像采集设备仅需要一个数据线对采集的图像进行传输，能够减小图像采集设备与 图像处理设备之间连接线的内径，使得该三维成像系统能够应用于尺寸较小的人体器官内，对人体器官进行三维成像，进一步提高了三维成像系统的使用范围。
通过参考附图会更加清楚的理解本发明的特征和优点，附图是示意性的而不应理解为对本发明进行任何限制，在附图中：
图1示出了本发明实施例中二维图像转换成三维图像的方法的一个具体示意的方法流程图；
图2示出了本发明实施例中收敛角与左右眼图像之间距离的关系的示意图；
图3示出了本发明实施例中二维图像转换成三维图像的方法的另一个具体示意的方法流程图；
图4示出了本发明实施例中线性缩放的原理示意图；
图5示出了本发明实施例中二维图像转换成三维图像的方法的另一个具体示意的方法流程图；
图6示出了本发明实施例中二维图像转换成三维图像的装置的一个具体示意的结构示意图；
图7示出了本发明实施例中二维图像转换成三维图像的装置的另一个具体示意的结构示意图；
图8示出了本发明实施例中图像处理设备的一个具体示意的结构示意图；
图9示出了本发明实施例中三维成像系统的一个具体示意的结构示意 图。
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
本发明提供的二维图像转换成三维图像的方法，通过将二维图像经过透视变换，创造出双眼视差图像，即左眼图像以及右眼图像，实现立体视觉；此外，通过调节左眼图像与右眼图像之间的距离，创建收敛角；利用双眼视差图像，结合收敛角，即可形成3D图像。
本发明实施例提供了一种二维图像转换成三维图像的方法，如图1所示，该方法包括：
S11，获取待处理二维图像。
二维图像转换成三维图像的装置获取到的待处理二维图像可以是二维图片；也可以是视频流中的一帧图像；也可以是实时采集视频，并从中提取出每帧图像，只需保证该二维图像转换成三维图像的装置获取到待处理二维图像即可。
S12，对待处理二维图像进行透视变换，分别得到左眼图像和右眼图像。
其中，透视变换为按照预设规则对待处理二维图像进行映射。二维图像转换成三维图像的装置按照预设规则对待处理二维图像进行映射，即在待处理二维图像的基础上，根据透视变换，通过图像处理形成左眼图像以 及右眼图像。其中，预设规则用于表示透视变换的方法，例如，变换后的图像近端显大，远端显小；也可以是通过公式计算出透视后图像等等。
S13，根据透视变换的结果，调节左眼图像与右眼图像之间的距离。
二维图像转换成三维图像的装置调节透视变换之后形成的左眼图像以及右眼图像之间的距离，用于创造出收敛角。
发明人通过多次实验得出，图像之间的距离发生改变时，相应的收敛角改变。例如，如图2所示，描述了收敛角与左右眼图像之间的距离的关系，如图2a)所示，当收敛角为α1时，左右眼之间的距离较小；如图2b)所示，当收敛角为α2时，左右眼之间的距离较大；即随着左右眼之间的距离的变换，收敛角也会产生相应的变化。因此，本发明中通过调教左右眼之间的距离，创造出收敛角。
S14，合成距离调节后的左眼图像以及右眼图像。
二维图像转换成三维图像的装置将调节后的左眼图像以及右眼图像进行合成，即利用经过图像变换创造出的双目视差以及收敛角，并将距离调节和的左眼图像以及右眼图像合成后输出至图像显示设备，用于后续的三维图像显示。其中，后续图像显示设备可以通过调节左眼图像与右眼图像的偏振方向，使得两幅图像的偏振方向相互垂直，用户在使用时，佩戴3D眼镜即可实现3D图像的观看；也可以采用其他方式实现偏振方向的调节，只需保证在人的两只眼睛分别看见的两幅图像的偏振方向相互垂直即可。
本发明实施例通过对待处理二维图像进行透视变换，创造出双眼视差图像，实现立体视觉；并将经过透视变换的左眼图像以及右眼图像进行距离的调节，形成双目视差，创建收敛角，使肉眼观察的图像位于不同的深 度处，从而可以看到不同的立体效果。即，通过对二维图像进行图像变换，并不涉及图像的分辨率以及清晰度，进而3D成像的图像与原始的二维图像的图像质量相同，并不影响3D成像的效果。
本发明实施例还提供了一种二维图像转换成三维图像的方法，如图3所示，该方法包括：
S21，获取待处理二维图像。
本实施例中待处理二维图像为视频流中的一帧图像，二维图像转换成三维图像的装置从视频流中依次提取每帧图像，用作待处理二维图像。因此，本实施例提供的方法能够实时将该装置采集到的视频流转换成3D视频。
S22，对待处理二维图像进行透视变换，分别得到左眼图像和右眼图像。
其中，透视变换为按照预设规则对待处理二维图像进行映射。本实施例中的二维图像转换成三维图像的装置中设置有图像模板，该图像模板用于对待处理二维图像进行归一化处理。
具体地，包括以下步骤：
S221，将待处理二维图像对齐到图像模板上，提取待处理二维图像的尺寸。
二维图像转换成三维图像的装置在获取到待处理二维图像之后，将待处理二维图像对齐到图像模板上，对待处理二维图像进行等比例缩放，以保证待处理二维图像不超出该图像模板的范围。
将待处理二维图像对齐到图像模板上之后，提取待处理二维图像的尺寸，该尺寸用于表示待处理二维图像的各边尺寸。
S222，按照预设规则依次对尺寸进行线性缩放，得到第一图像。
其中，线性缩放的原理如图4所示，透视变换为对原始图像的左侧的边为旋转轴，向屏幕内部翻转一定角度，以及向屏幕外旋转相同的角度，分别形成于图4中间以及最右边的图像。本实施例中通过线性缩放待处理二维图像的尺寸，使得缩放后的左右眼图像达到图4所示的效果。具体可以包括以下步骤：
1)逐行扫描待处理二维图像。
二维图像转换成三维图像的装置将对齐到图像模板上的待处理二维图像进行逐行扫描，获取待处理二维图像每行的尺寸。
2)依次对每行的图像进行线性缩放。
二维图像转换成三维图像的装置按照一端显大，另一端显小的原则，对待处理二维图像的每行尺寸进行线性缩放，得到尺寸缩放后的第一图像。通过依次对每行进行线性缩放，减小了处理的数据量，能够实现二维图像的实时转换
S223，镜像处理第一图像，得到第二图像。
二维图像转换成三维图像的装置对第一图像进行镜像处理，得到第二图像；即，对第一图像沿竖直方向进行镜像处理，得到第二图像。
其中，第一图像为左眼图像，第二图像为右眼图像；或，第一图像为右眼图像，第二图像为左眼图像。
S23，根据透视变换的结果，调节左眼图像与右眼图像之间的距离。
二维图像转换成三维图像的装置在形成左眼图像以及右眼图像之后，将左眼图像以及右眼图像重合后，调节左眼图像与右眼图像之间的距离， 使得两幅图像发生重影。
S24，合成距离调节后的左眼图像以及右眼图像。
二维图像转换成三维图像的装置将距离调节后的左眼图像以及右眼图像的重影重新重合到一起，用于在图像显示设备上进行3D图像的显示。
与图1所示实施例的二维图像转换成三维图像的方法相比，本实施例中通过将二维图像通过线性缩放转换为对应于左右眼的两幅图像，即，将无视差的2D图像转换成具有视差的左眼图像与右眼图像，该转换过程仅涉及图像尺寸而与图像质量无关，因此经过线性缩放所形成的左眼图像以及右眼图像与原始二维图像的质量相同。本发明实施例提供的转换方法能够在保证图像质量不变的前提下，形成左眼图像以及右眼图像。
本实施例还提供了一种二维图像转换成三维图像的方法，如图5所示，该方法包括：
S31，获取待处理二维图像。与图3所示实施例的S21相同，在此不再赘述。
S32，对待处理二维图像进行透视变换，分别得到左眼图像和右眼图像。与图3所示实施例的S22相同，在此不再赘述。
S33，根据透视变换的结果，调节左眼图像与所述右眼图像之间的距离。
本实施例中，利用对待处理二维图像进行归一化处理的图像模板，进行左眼图像以及右眼图像之间距离的调节。具体地，包括以下步骤：
S331，将左眼图像与右眼图像同时对齐到图像模板上。
二维图像转换成三维图像的装置将左眼图像以及右眼图像同时对齐到图像模板上，即以图像模板为基准对左右眼图像进行平移，在不增加数据 处理量的前提下，能够保证较好的平移效果，提高二维图像的转换效率。
S332，沿第一方向平移左眼图像或右眼图像，使得左眼图像与右眼图像之间的距离达到预设距离。
本实施例中，第一方向为水平方向，将对齐到图像模板上的左右眼图像中的一个图像沿水平方向平移，使得左右眼图像之间的距离达到预设距离，或者同时沿相反方向移动左右眼图像。其中，预设距离可以根据实际显示设备的尺寸进行具体设置。
S34，合成距离调节后的左眼图像以及右眼图像。与图3所示实施例的S24相同，在此不再赘述。
与图3所示实施例的二维图像转换成三维图像的方法相比，本实施例中通过利用同一图像模板形成左眼图像和右眼图像，以及对左眼图像和右眼图像进行平移，创造出双眼视差以及收敛角，提高了转换效率。
本发明实施例还提供了一种二维图像转换成三维图像的装置，如图6所示，该装置包括：
获取模块41，用于获取待处理二维图像。
透视变换模块42，用于对待处理二维图像进行透视变换，分别得到左眼图像和右眼图像，其中，透视变换为按照预设规则对待处理二维图像进行映射。
调节模块43，用于根据透视变换的结果，调节左眼图像与右眼图像之间的距离。
合成模块44，用于合成距离调节后的左眼图像以及右眼图像。
本发明实施例中提供的二维图像转换成三维图像的装置，通过对待处 理二维图像进行透视变换，创造出双眼视差图像，实现立体视觉；并将经过透视变换的左眼图像以及右眼图像进行距离的调节，形成双目视差，创建收敛角，使肉眼观察的图像位于不同的深度处，从而可以看到不同的立体效果。即，通过对二维图像进行图像变换，并不涉及图像的分辨率以及清晰度，进而3D成像的图像与原始的二维图像的图像质量相同，并不影响3D成像的效果。
在本实施例的一些可选实施方式中，如图7所示，透视变换模块42，包括：
提取单元421，用于将待处理二维图像对齐到图像模板上，提取待处理二维图像的尺寸。
线性缩放单元422，用于按照预设规则依次对尺寸进行线性缩放，得到第一图像。
镜像单元423，用于镜像处理第一图像，得到第二图像；其中，第一图像为左眼图像，第二图像为右眼图像；或，第一图像为所述右眼图像，第二图像为左眼图像。
本发明实施例还提供了一种图像处理设备，如图8所示，该图像处理设备可以包括处理器51和存储器52，其中处理器51和存储器52可以通过总线或者其他方式连接，图8中以通过总线连接为例。
处理器51可以为中央处理器(Central Processing Unit，CPU)。处理器51还可以为其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field-Programmable Gate Array， FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等芯片，或者上述各类芯片的组合。
存储器52作为一种非暂态计算机可读存储介质，可用于存储非暂态软件程序、非暂态计算机可执行程序以及模块，如本发明实施例中的二维图像转换成三维图像的方法对应的程序指令/模块(例如，图6所示的第获取模块41、透视变换模块42、调节模块43和合成模块44)。处理器51通过运行存储在存储器52中的非暂态软件程序、指令以及模块，从而执行处理器的各种功能应用以及数据处理，即实现上述方法实施例中的二维图像转换成三维图像的方法。
存储器52可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储处理器51所创建的数据等。此外，存储器52可以包括高速随机存取存储器，还可以包括非暂态存储器，例如至少一个磁盘存储器件、闪存器件、或其他非暂态固态存储器件。在一些实施例中，存储器52可选包括相对于处理器51远程设置的存储器，这些远程存储器可以通过网络连接至处理器51。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
所述一个或者多个模块存储在所述存储器52中，当被所述处理器51执行时，执行如图1，图3以及图5所示实施例中的二维图像转换成三维图像的方法。
上述图像处理设备具体细节可以对应参阅图1，图3以及图5所示的实施例中对应的相关描述和效果进行理解，此处不再赘述。
本发明实施例还提供了一种三维成像系统，如图9所示，该系统包括：图像采集设备61，图像处理设备62以及图像显示设备63。
其中，图像采集设备61中，用于采集图像的镜头由单镜头组成。图像处理设备62与图像采集设备61电连接，用于将图像采集设备61输出的待处理二维图像转换成三维图像。图像显示设备63，与图像处理设备62电连接，用于显示图像处理设备62输出的三维图像。
本发明实施例提供的三维成像系统，其中，在图像采集设备61的镜头由单镜头组成，减小了整个图像采集设备61的体积；此外，单镜头的图像采集设备仅需要一个数据线对采集的图像进行传输，能够减小图像采集设备61与图像处理设备62之间连接线的内径，使得该三维成像系统能够应用于尺寸较小的物体内部，例如人体器官内，对人体器官进行三维成像，进一步提高了三维成像系统的使用范围。
本领域技术人员可以理解，实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述存储介质可为磁碟、光盘、只读存储记忆体(Read-OnlyMemory，ROM)、随机存储记忆体(Random Access Memory，RAM)、快闪存储器(Flash Memory)、硬盘(Hard Disk Drive，缩写：HDD)或固态硬盘(Solid-State Drive，SSD)等；所述存储介质还可以包括上述种类的存储器的组合。
虽然结合附图描述了本发明的实施例，但是本领域技术人员可以在不脱离本发明的精神和范围的情况下作出各种修改和变型，这样的修改和变 型均落入由所附权利要求所限定的范围之内。
Claims (10)
- 一种二维图像转换成三维图像的方法，其特征在于，包括：获取待处理二维图像；对所述待处理二维图像进行透视变换，分别得到左眼图像和右眼图像，其中，所述透视变换为按照预设规则对所述待处理二维图像进行映射；根据所述透视变换的结果，调节所述左眼图像与所述右眼图像之间的距离；合成距离调节后的所述左眼图像以及所述右眼图像。
- 根据权利要求1所述的方法，其特征在于，所述对所述待处理二维图像进行透视变换，包括：将所述待处理二维图像对齐到图像模板上，提取所述待处理二维图像的尺寸；按照所述预设规则依次对各边所述尺寸进行线性缩放，得到第一图像；镜像处理所述第一图像，得到第二图像；其中，所述第一图像为所述左眼图像，所述第二图像为所述右眼图像；或，所述第一图像为所述右眼图像，所述第二图像为所述左眼图像。
- 根据权利要求2所述的方法，其特征在于，所述按照所述预设规则依次对各边所述尺寸进行线性缩放，包括：逐行扫描所述待处理二维图像；依次对每行的图像进行所述线性缩放。
- 根据权利要求2所述的方法，其特征在于，所述根据所述透视变换的结果，调节所述左眼图像与所述右眼图像之间的距离，包括：将所述左眼图像与所述右眼图像同时对齐到所述图像模板上；沿第一方向平移所述左眼图像或右眼图像，使得所述左眼图像与所述右眼图像之间的距离达到预设距离。
- 根据权利要求1所述的方法，其特征在于，所述待处理二维图像为视频流中的一帧图像。
- 一种二维图像转换成三维图像的装置，其特征在于，包括：获取模块，用于获取待处理二维图像；透视变换模块，用于对所述待处理二维图像进行透视变换，分别得到左眼图像和右眼图像，其中，所述透视变换为按照预设规则对所述待处理二维图像进行映射；调节模块，用于根据所述透视变换的结果，调节所述左眼图像与所述右眼图像之间的距离；合成模块，用于合成距离调节后的所述左眼图像以及所述右眼图像。
- 根据权利要求6所述的装置，其特征在于，透视变换模块，包括：提取单元，用于将所述待处理二维图像对齐到图像模板上，提取所述待处理二维图像的尺寸；线性缩放单元，用于按照所述预设规则依次对各边所述尺寸进行线性缩放，得到第一图像；镜像单元，用于镜像处理所述第一图像，得到第二图像；其中，所述第一图像为所述左眼图像，所述第二图像为所述右眼图像；或，所述第一图像为所述右眼图像，所述第二图像为所述左眼图像。
- 一种图像处理设备，其特征在于，包括：存储器和处理器，所述存储器和所述处理器之间互相通信连接，所述 存储器中存储有计算机指令，所述处理器通过执行所述计算机指令，从而执行权利要求1-5任一项所述的二维图像转换成三维图像的方法。
- 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机指令，所述计算机指令用于使所述计算机执行权利要求1-5任一项所述的二维图像转换成三维图像方法。
- 一种三维成像系统，其特征在于，包括：图像采集设备，采集图像的镜头由单镜头组成；权利要求8所述的图像处理设备，与所述图像采集设备电连接，用于将二维图像转换成三维图像；图像显示设备，与所述图像处理设备电连接，用于显示所述三维图像。
Priority Applications (6)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| ES202090055A ES2813425A1 (es) | 2018-04-27 | 2019-05-06 | Metodo y dispositivo para convertir una imagen 2d en una imagen 3d y sistema de formacion de imagenes 3d |
| JP2020564472A JP7112128B2 (ja) | 2018-04-27 | 2019-05-06 | ２次元画像を３次元画像に変換する方法、装置、画像処理機器、記憶媒体及び３次元イメージングシステム |
| CA3100255A CA3100255C (en) | 2018-04-27 | 2019-05-06 | Method and device for converting two-dimensional image into three-dimensional image and three-dimensional imaging system |
| DE112019002445.0T DE112019002445T5 (de) | 2018-04-27 | 2019-05-06 | Verfahren, Vorrichtung zur Bildumwandlung von 2D in 3D und dreidimensionales Bildgebungssystem |
| US17/055,257 US11589030B2 (en) | 2018-04-27 | 2019-05-06 | Method and device for converting 2D image into 3D image and 3D imaging system |
| RU2020140940A RU2762068C1 (ru) | 2018-04-27 | 2019-05-06 | Способ и устройство преобразования двухмерного изображения в трехмерное изображение и система трехмерной визуализации |
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810391484 | 2018-04-27 | ||
| CN201810456740.4 | 2018-05-14 | ||
| CN201810456740.4A CN108712643B (zh) | 2018-04-27 | 2018-05-14 | 二维图像转换成三维图像的方法、装置及三维成像系统 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2019218887A1 true WO2019218887A1 (zh) | 2019-11-21 |
Family
ID=63869032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2019/085688 WO2019218887A1 (zh) | 2018-04-27 | 2019-05-06 | 二维图像转换成三维图像的方法、装置及三维成像系统 |
Country Status (8)
| Country | Link |
|---|---|
| US (1) | US11589030B2 (zh) |
| JP (1) | JP7112128B2 (zh) |
| CN (1) | CN108712643B (zh) |
| CA (1) | CA3100255C (zh) |
| DE (1) | DE112019002445T5 (zh) |
| ES (1) | ES2813425A1 (zh) |
| RU (1) | RU2762068C1 (zh) |
| WO (1) | WO2019218887A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949551A (zh) * | 2021-03-19 | 2021-06-11 | 科大讯飞股份有限公司 | 一种眼部关键信息确定方法、装置、设备及存储介质 |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108712643B (zh) | 2018-04-27 | 2020-02-21 | 苏州新光维医疗科技有限公司 | 二维图像转换成三维图像的方法、装置及三维成像系统 |
| CN108737810B (zh) * | 2018-05-23 | 2019-08-06 | 苏州新光维医疗科技有限公司 | 图像处理方法、装置及三维成像系统 |
| JP7393424B2 (ja) * | 2018-11-15 | 2023-12-06 | 中国科学院大▲連▼化学物理研究所 | 階層的細孔を有するｔｓ－１分子篩の製造方法 |
| CN111988533B (zh) * | 2019-05-23 | 2022-07-22 | 川田科技株式会社 | 焊接辅助方法及装置 |
| CN110995997A (zh) * | 2019-12-11 | 2020-04-10 | 苏州新光维医疗科技有限公司 | 一种单镜头内窥镜图像处理转换方法 |
| CN111246012B (zh) * | 2020-01-06 | 2022-09-16 | 北京小米移动软件有限公司 | 应用界面显示方法、装置及存储介质 |
| CN111935473B (zh) * | 2020-08-17 | 2022-10-11 | 广东申义实业投资有限公司 | 一种快速眼部三维图像采集器及其图像采集方法 |
| CN112383765B (zh) * | 2020-11-10 | 2023-04-07 | 中移雄安信息通信科技有限公司 | 一种vr图像传输方法及装置 |
| CN115190286B (zh) * | 2022-07-06 | 2024-02-27 | 敏捷医疗科技(苏州)有限公司 | 一种2d图像转换方法及装置 |
| CN115713465B (zh) * | 2022-10-28 | 2023-11-14 | 北京阅友科技有限公司 | 平面图像的立体展示方法及装置、存储介质、终端 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1997015150A1 (fr) * | 1995-10-19 | 1997-04-24 | Sony Corporation | Procede et dispositif de formation d'images en trois dimensions |
| CN103329547A (zh) * | 2010-12-06 | 2013-09-25 | 泰拉奈克斯系统公司 | 伪3d强迫透视方法及设备 |
| CN108712643A (zh) * | 2018-04-27 | 2018-10-26 | 苏州新光维医疗科技有限公司 | 二维图像转换成三维图像的方法、装置及三维成像系统 |
| CN108737810A (zh) * | 2018-05-23 | 2018-11-02 | 苏州新光维医疗科技有限公司 | 图像处理方法、装置及三维成像系统 |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7477323B2 (en) * | 2005-11-07 | 2009-01-13 | Kolorific, Inc. | Method and system for digital image magnification and reduction |
| US7573489B2 (en) * | 2006-06-01 | 2009-08-11 | Industrial Light & Magic | Infilling for 2D to 3D image conversion |
| RU92595U1 (ru) * | 2009-12-24 | 2010-03-20 | Михаил Михайлович Слепко | Устройство для формирования 3d стереоскопического изображения из 2d моноскопического изображения |
| US8908011B2 (en) * | 2010-09-17 | 2014-12-09 | Panasonic Corporation | Three-dimensional video creating device and three-dimensional video creating method |
| TWI489414B (zh) * | 2011-07-25 | 2015-06-21 | Realtek Semiconductor Corp | ２ｄ轉３ｄ影像轉換裝置及其方法 |
| CN102905141A (zh) * | 2011-07-28 | 2013-01-30 | 联咏科技股份有限公司 | 二维转三维转换装置及其方法 |
| CN102438161A (zh) * | 2011-08-19 | 2012-05-02 | 四川长虹电器股份有限公司 | 二维图像转三维图像的方法 |
| JP2013115668A (ja) * | 2011-11-29 | 2013-06-10 | Sony Corp | 画像処理装置、および画像処理方法、並びにプログラム |
| US20160094837A1 (en) * | 2014-09-30 | 2016-03-31 | 3DOO, Inc. | Distributed stereoscopic rendering for stereoscopic projecton and display |
| CN104683784A (zh) * | 2015-02-04 | 2015-06-03 | 长春理工大学 | 一种基于图像错切变换的全自动2d转3d视频方法 |
| CN105376546A (zh) * | 2015-11-09 | 2016-03-02 | 中科创达软件股份有限公司 | 一种2d转3d方法、装置及移动终端 |
-
2018
- 2018-05-14 CN CN201810456740.4A patent/CN108712643B/zh active Active
-
2019
- 2019-05-06 US US17/055,257 patent/US11589030B2/en active Active
- 2019-05-06 DE DE112019002445.0T patent/DE112019002445T5/de active Pending
- 2019-05-06 ES ES202090055A patent/ES2813425A1/es active Pending
- 2019-05-06 JP JP2020564472A patent/JP7112128B2/ja active Active
- 2019-05-06 RU RU2020140940A patent/RU2762068C1/ru active
- 2019-05-06 CA CA3100255A patent/CA3100255C/en active Active
- 2019-05-06 WO PCT/CN2019/085688 patent/WO2019218887A1/zh active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1997015150A1 (fr) * | 1995-10-19 | 1997-04-24 | Sony Corporation | Procede et dispositif de formation d'images en trois dimensions |
| CN103329547A (zh) * | 2010-12-06 | 2013-09-25 | 泰拉奈克斯系统公司 | 伪3d强迫透视方法及设备 |
| CN108712643A (zh) * | 2018-04-27 | 2018-10-26 | 苏州新光维医疗科技有限公司 | 二维图像转换成三维图像的方法、装置及三维成像系统 |
| CN108737810A (zh) * | 2018-05-23 | 2018-11-02 | 苏州新光维医疗科技有限公司 | 图像处理方法、装置及三维成像系统 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949551A (zh) * | 2021-03-19 | 2021-06-11 | 科大讯飞股份有限公司 | 一种眼部关键信息确定方法、装置、设备及存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CA3100255C (en) | 2023-09-26 |
| JP7112128B2 (ja) | 2022-08-03 |
| RU2762068C1 (ru) | 2021-12-15 |
| CN108712643B (zh) | 2020-02-21 |
| ES2813425A1 (es) | 2021-03-23 |
| DE112019002445T5 (de) | 2021-03-04 |
| CA3100255A1 (en) | 2019-11-21 |
| CN108712643A (zh) | 2018-10-26 |
| US20210127107A1 (en) | 2021-04-29 |
| JP2021524969A (ja) | 2021-09-16 |
| US11589030B2 (en) | 2023-02-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019218887A1 (zh) | 二维图像转换成三维图像的方法、装置及三维成像系统 | |
| EP3067746B1 (en) | Photographing method for dual-camera device and dual-camera device | |
| WO2019223523A1 (zh) | 图像处理方法、装置及三维成像系统 | |
| WO2016000527A1 (zh) | 广域图像获取方法和装置 | |
| WO2010119852A1 (ja) | 任意視点画像合成装置 | |
| US20110150101A1 (en) | 3d video communication method, sending device and system, image reconstruction method and system | |
| US20160295194A1 (en) | Stereoscopic vision system generatng stereoscopic images with a monoscopic endoscope and an external adapter lens and method using the same to generate stereoscopic images | |
| JP2011525075A (ja) | 移動機器用立体画像生成チップ及びこれを用いた立体画像表示方法 | |
| US20130050187A1 (en) | Method and Apparatus for Generating Multiple Image Views for a Multiview Autosteroscopic Display Device | |
| US20130202191A1 (en) | Multi-view image generating method and apparatus using the same | |
| CN106228530B (zh) | 一种立体摄影方法、装置及立体摄影设备 | |
| CN103488040A (zh) | 立体全景影像合成方法及其相关的立体摄影机 | |
| JP2012085102A (ja) | 立体映像変換装置及び立体映像表示装置 | |
| KR20050083352A (ko) | 휴대용 단말장치에서 스테레오 카메라를 이용하여 파노라믹 영상과 3차원 영상을 획득 및 디스플레이를 할 수 있는 장치 및 그 방법. | |
| WO2020244273A1 (zh) | 双摄像机三维立体成像系统和处理方法 | |
| CN115222793A (zh) | 深度图像的生成及显示方法、装置、系统、可读介质 | |
| JP2011182003A (ja) | パノラマカメラ及び３６０度パノラマ立体映像システム | |
| JP5297899B2 (ja) | 立体映像調整装置、立体映像調整システム、及びプログラム | |
| CN113741136B (zh) | 一种摄像装置 | |
| JP2013046081A (ja) | 撮影装置および映像生成方法 | |
| JP7336871B2 (ja) | 全天周映像処理装置及びプログラム | |
| KR20060121016A (ko) | 입체영상 생성장치 | |
| TW201514926A (zh) | 視差計算方法及其立體匹配系統 | |
| TW201531276A (zh) | 使用色度成形法的內視鏡立體視覺化系統及方法 | |
| JP2007194694A (ja) | 立体映像撮影装置並びにそのプログラム |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19802543 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2020564472 Country of ref document: JP Kind code of ref document: A |
|
| ENP | Entry into the national phase |
Ref document number: 3100255 Country of ref document: CA |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 19802543 Country of ref document: EP Kind code of ref document: A1 |