CN102932658A - Method for realizing 2D-to-3D (two-dimension to three-dimension) conversion based on image segmentation technology - Google Patents

Abstract

The invention relates to a method for realizing 2D-to-3D (two-dimension to three-dimension) conversion based on an image segmentation technology. The method is characterized by comprising the following steps of: (1) receiving original 2D images and buffering first frame data; (2) buffering next frame data; (3) extracting non-output previous frame data and calculating the gray-scale value of each pixel of the images; (4) sequencing the gray-scale values of all pixels in an ascending order and saving a result; (5) setting a standard gray-scale value h; (6) carrying out left-and-right separation on the pixels with the gray-scale values greater than h; and (7) respectively outputting left-eye images and right-eye images to a display screen in a timesharing manner. According to the method disclosed by the invention, the gray-scale value of each pixel is extracted, the sequencing is carried out according to the gray-scale values, the fixed gray-scale value h is taken as a demarcation criterion of the sequenced result, image contours are determined, the left-eye images and the right-eye images are separated on the basis that the contours are known, and shutter-type 3D glasses are used in a matching manner, thus the 3D effect is realized.

Description

A kind of method that turns 3D based on image Segmentation Technology realization 2D

Technical field

The present invention relates to a kind of method that turns 3D based on image Segmentation Technology realization 2D.

Background technology

Present stage, the 3D technology develops at a terrific speed.Along with the concern of people to the 3D technology, increasing producer releases the novel product of supporting that 3D shows.The 3D TV, 3D projector, the 3D mobile phone, the carry-on video player of 3D etc. just progressively enters into ordinary people's family.But because the quantity problem of 3D film source, the equipment that great majority support 3D to show often can not be given full play to its effect.Exactly because so, convert the technology of 3D video to by traditional 2D video, received the concern of each producer.

For original 2D image or video, be fit to the image that 3D shows if want to be converted to, need in original image, isolate the picture of left eye and right eye, and the image of left eye and right eye is processed according to diverse ways, and produce 3D effect by glasses.And the most difficult among this be the image of separate left and right eye.

Summary of the invention

The purpose of this invention is to provide a kind of method that turns 3D based on image Segmentation Technology realization 2D, can realize 3D effect by the processing to image.

A kind of method that turns 3D based on image Segmentation Technology realization 2D, its special feature is, comprises the steps:

(1) receives original 2D image and with the first frame data buffer memory;

(2) buffer memory next frame data;

(3) the previous frame data of will not exporting extract, each pixel gray value in the computed image;

(4) gray value of all pixels is arranged and event memory according to ascending order;

(5) established standards gray value h will carry out respectively mark less than h with greater than the pixel of h, and the pixel that equals h is mark not, and the mark result is carried out buffer memory;

(6) separate about gray value is carried out greater than the pixel of h, draw respectively left-eye image and eye image, then all carry out buffer memory;

(7) export respectively left-eye image and eye image to display screen in the mode of timesharing, produce the 3D rendering source that is applicable to shutter glasses;

(8) extracting the next frame image returns step (2) and processes.

The inventive method is by extracting the gray value of each pixel, and sort according to gray value, with the result after the ordering with fixing gray value h as the boundary standard, determine image outline, on the basis of known profile, isolate the image of left eye and right eye, thereby cooperate shutter type 3 D spectacles to realize 3D effect.Through evidence, 3D effect is comparatively obvious.

Description of drawings

Accompanying drawing 1 is for adopting the inventive method to carry out the schematic diagram of separation of images.

Embodiment

As shown in Figure 1, adopt the inventive method at first to want each gray value of computed image to get distribution frequency, then calculator cumulative distribution frequency.If n pixel arranged in the image, lowest gray value and the highest gray value in Hmin and the Hmax difference presentation video carry out ascending order according to order from low to high and arrange.As benchmark, will carry out respectively mark with fixing gray value h less than gray value h with greater than the pixel of gray value h, will be defined as image outline greater than the pixel of gray value h, and the wire-frame image vegetarian refreshments is stored.Take the wire-frame image vegetarian refreshments as benchmark, original image is separated into left eye and right eye two width of cloth images, and respectively storage, finish the separation of image.

Embodiment 1:

A kind of method that turns 3D based on image Segmentation Technology realization 2D comprises the steps:

(1) receives original 2D image and with the first frame data buffer memory;

(2) buffer memory next frame data;

(3) the previous frame data of will not exporting extract, each pixel gray value in the computed image;

(4) gray value of all pixels is arranged and event memory according to ascending order;

(5) (h is summed up by internal data and sets established standards gray value h, adopt the arithmetic mean of all pixel gray values in this example), to carry out respectively mark less than h with greater than the pixel of h, the pixel that equals h is mark not, and the mark result is carried out buffer memory;

(6) about being carried out greater than the pixel of h, separates gray value, can (n can set according to the demand of the depth of field to a left n pixel or to a right translation n pixel, in this example to 192 pixels of right translation), draw respectively left-eye image and eye image, then all carry out buffer memory;

(7) export respectively left-eye image and eye image to display screen in the mode of timesharing, produce the 3D rendering source that is applicable to shutter glasses;

(8) extract the second two field picture and return step (2) and process, until change complete.

Claims (1)

1. a method that turns 3D based on image Segmentation Technology realization 2D is characterized in that, comprises the steps:

(1) receives original 2D image and with the first frame data buffer memory;

(2) buffer memory next frame data;

(3) the previous frame data of will not exporting extract, each pixel gray value in the computed image;

(4) gray value of all pixels is arranged and event memory according to ascending order;

(5) established standards gray value h will carry out respectively mark less than h with greater than the pixel of h, and the pixel that equals h is mark not, and the mark result is carried out buffer memory;

(6) separate about gray value is carried out greater than the pixel of h, draw respectively left-eye image and eye image, then all carry out buffer memory;

(7) export respectively left-eye image and eye image to display screen in the mode of timesharing, produce the 3D rendering source that is applicable to shutter glasses;

(8) extracting the next frame image returns step (2) and processes.

Images