CN117635684A - Stereo format image detection method and electronic device using same - Google Patents

Abstract

The invention provides a stereoscopic format image detection method and an electronic device using the same. The stereoscopic format image detection method includes the following steps. The input image is segmented according to a stereoscopic image format to obtain a first image and a second image. And performing stereo matching processing on the first image and the second image to generate a parallax image of the first image and the second image. And calculating the matching quantity of a plurality of first pixels in the first image and a plurality of second pixels in the second image according to the parallax map. And judging whether the input image is a stereoscopic format image conforming to the stereoscopic image format according to the matching quantity. Thus, whether the input image is a stereoscopic format image can be accurately distinguished.

Description

Stereo format image detection method and electronic device using same

Technical Field

The present invention relates to electronic devices, and more particularly, to a stereoscopic image detection method and an electronic device using the same.

Background

With the progress of display technology, displays supporting three-dimensional (3D) image playback have become popular. The difference between the 3D display and the two-dimensional (2D) display is that the 3D display technology can make the viewer feel the stereoscopic impression in the image, such as the stereoscopic five sense organs and depth of field (depth of field) of the person, while the conventional 2D image cannot show such effect. The principle of the 3D display technology is to let the left eye of the viewer watch the left eye image and the right eye of the viewer watch the right eye image, so that the viewer can feel the 3D visual effect. With the vigorous development of 3D stereoscopic display technology, people can be provided with the visual experience of body calendar. It can be known that the 3D display needs to use a corresponding 3D display technology to play the image with a specific 3D image format, otherwise, the 3D display cannot display the image correctly. Therefore, how to accurately recognize image content conforming to a specific 3D image format is an issue of concern to those skilled in the art.

Disclosure of Invention

The invention relates to a stereoscopic format image detection method and an electronic device using the same, which can accurately distinguish whether an input image is a stereoscopic format image.

The embodiment of the invention provides a stereoscopic format image detection method which is suitable for an electronic device and comprises the following steps. The input image is segmented according to a stereoscopic image format to obtain a first image and a second image. The first image and the second image are subjected to stereo matching processing to generate a disparity map (disparity map) of the first image and the second image. And calculating the matching quantity of a plurality of first pixels in the first image and a plurality of second pixels in the second image according to the parallax map. And judging whether the input image is a stereoscopic format image conforming to the stereoscopic image format according to the matching quantity.

The embodiment of the invention provides an electronic device which comprises a storage device and a processor. The processor is connected with the storage device and is configured to execute the following steps. The input image is segmented according to a stereoscopic image format to obtain a first image and a second image. And performing stereo matching processing on the first image and the second image to generate a parallax image of the first image and the second image. And calculating the matching quantity of a plurality of first pixels in the first image and a plurality of second pixels in the second image according to the parallax map. And judging whether the input image is a stereoscopic format image conforming to the stereoscopic image format according to the matching quantity.

Based on the above, in the embodiment of the invention, the input image is divided based on the stereoscopic image format to acquire the first image and the second image. A disparity map is obtained by performing stereo matching processing on the first image and the second image. Whether the input image conforms to the stereoscopic image format may be determined based on the matching condition of the disparity map. Therefore, whether the input image is a stereoscopic format image can be effectively judged, and therefore the user experience and the application range of the 3D display technology are improved.

Drawings

FIG. 1 is a schematic diagram of an electronic device according to an embodiment of the invention;

FIG. 2 is a flow chart of a method for detecting stereoscopic format images according to an embodiment of the invention;

FIGS. 3A-3D are schematic diagrams of cutting an input image according to an embodiment of the invention;

FIG. 4 is a flowchart of determining whether an input image is a stereoscopic format image according to an embodiment of the present invention;

FIG. 5 is a flow chart of a method for detecting stereoscopic format images according to an embodiment of the invention;

fig. 6 is a schematic diagram of acquiring a disparity map according to an embodiment of the present invention.

Description of the reference numerals

100, an electronic device;

110, a storage device;

120, a processor;

a 20:3d display;

IMG_i1, IMG_i2, IMG_i3, IMG_i4, IMG1: input image;

IMG_31, IMG_33, IMG_35, IMG_37, IMG_L, a first image;

IMG_32, IMG_34, IMG_36, IMG_38, IMG_R, a second image;

d_map, disparity map;

r1 is a matching proportion;

p1 is a first target pixel point;

p2 is a second target pixel point;

b1, a first target image block;

b2_1 to B2_9, a second image block;

SL1, horizontal scanning line;

c1, similarity curve;

y1 is Y axis position;

x1, X2, X axis position;

d1, effective parallax value;

s210 to S240, S241 to S243, and S502 to S512.

Detailed Description

Reference will now be made in detail to the exemplary embodiments of the present invention, examples of which are illustrated in the accompanying drawings. Wherever possible, the same reference numbers will be used throughout the drawings and the description to refer to the same or like parts.

Fig. 1 is a schematic diagram of an electronic device according to an embodiment of the invention. Referring to fig. 1, an electronic device 10 may include a memory device 110 and a processor 120. The processor 120 is coupled to the storage device 110. The electronic device 10 may be implemented as a notebook computer, a smart phone, a tablet computer, a desktop computer, a set-top box or a gaming machine, and the like.

In one embodiment, the electronic device 10 may form a 3D display system with a stereoscopic (3D) display 20. The 3D display 20 may be a bare 3D display or a glasses type 3D display. Viewed from another aspect, the 3D display 20 may be a head mounted display device or a computer screen, desktop screen or television, or the like that provides 3D image display functionality. The 3D display system may be a single integrated system or a separate system. Specifically, the 3D display 20, the storage 110, and the processor 120 in the 3D display system may be implemented as an integrated-in-one (AIO) electronic device, such as a head-mounted display apparatus, a notebook computer, a smart phone, a tablet computer, or a game machine, etc. Alternatively, the 3D display 20 may be coupled to the processor 120 via a wired or wireless transmission interface, such as a head mounted display device, a desktop screen, a television or electronic billboard, and so forth.

The storage device 110 is used for storing images, data and data such as program codes (e.g. operating system, application programs, drivers) for accessing the processor 120, and may be, for example, any type of fixed or removable random access memory (random access memory, RAM), read-only memory (ROM), flash memory (flash memory), hard disk, or a combination thereof.

The processor 120 is coupled to a storage device 110, such as a central processing unit (central processing unit, CPU), an application processor (application processor, AP), or other general purpose or special purpose microprocessor (microprocessor), digital signal processor (digital signal processor, DSP), image signal processor (image signal processor, ISP), graphics processor (graphics processing unit, GPU), or other similar device, integrated circuit, or a combination thereof. The processor 120 may access and execute program codes and software modules recorded in the storage device 110 to implement the stereoscopic format image detection method in the embodiment of the present invention.

Generally, in order for a user to feel a 3D visual effect, the left and right eyes of the user need to view image contents (i.e., left and right eye images) corresponding to different viewing angles, respectively. The left eye image and the right eye image are synthesized into a stereoscopic format image, so that the stereoscopic format image is displayed through different 3D display technologies, and the left eye of an observer views the left eye image and the right eye of the observer views the right eye image. In an embodiment of the present invention, the electronic device 10 may determine whether the input image is a stereoscopic image conforming to the stereoscopic image format. Thus, in some embodiments, 3D display 20 may support multiple display modes, such as a 2D display mode and a 3D display mode associated with one or more 3D display technologies. If the electronic device 10 can accurately determine what stereoscopic format image the input image is, the 3D display 20 can automatically switch to a suitable display mode to display the stereoscopic image content.

Fig. 2 is a flowchart of a stereoscopic format image detection method according to an embodiment of the present invention. Referring to fig. 2, the manner of the present embodiment is applicable to the electronic device 10 in the above embodiment, and the detailed steps of the present embodiment are described below together with the components of the electronic device 10.

In step S210, the processor 120 divides the input image according to the stereoscopic image format to obtain a first image and a second image. In some embodiments, the input image may be a single frame image in a video stream or film. In some embodiments, the input image may be an image acquired using a screen capture function. In some embodiments, the input image may be, for example, an image generated by an application. In some embodiments, the first image size is the same as the second image size. In other words, the stereoscopic format image will be divided into two images of the same resolution.

In some embodiments, the stereoscopic image format may include a side-by-side format, a checkerboard format, or an interlaced format. The processor 120 will capture the first image and the second image from the stereoscopic image format based on the stereoscopic format. For example, fig. 3A to 3D are schematic diagrams of cutting an input image according to an embodiment of the invention.

Referring to the embodiment shown in fig. 3A, when it is detected whether the input image img_i1 conforms to the Side-by-Side (SBS) format, the processor 120 can cut the input image img_i1 into a first image img_31 on the left half and a second image img_32 on the right half.

Referring to the embodiment shown in fig. 3B, when it is detected whether the input image img_i2 conforms to the Top and Bottom (TB) format, the processor 120 may cut the input image img_i2 into a first image img_33 on the upper half and a second image img_34 on the lower half.

Referring to the embodiment shown in fig. 3C, when it is detected whether the input image img_i3 conforms to the interleaving (interleaving) format, the processor 120 may first cut the input image img_i3 into a plurality of sub-images img_s1 to img_s10 along the horizontal direction. Then, the processor 120 combines the sub-images img_s1, img_s3, img_s5, img_s7, img_s9 to obtain the first image img_35, and combines the sub-images img_s2, img_s4, img_s6, img_s8, img_s10 to obtain the second image img_36. However, the number of sub-images shown in FIG. 3C is merely exemplary and is not intended to limit the present invention.

Referring to the embodiment shown in fig. 3D, when detecting whether the input image img_i4 conforms to the CheckerBoard (CheckerBoard) format, the processor 120 may first cut the input image img_i4 into a plurality of sub-images (e.g. sub-images img_c1, img_c2, img_c3, img_c4) in a CheckerBoard arrangement according to the CheckerBoard pattern. Then, the processor 120 merges the plurality of sub-images (e.g., sub-images img_c1 and img_c3) to obtain a first image img_37, and merges the plurality of sub-images (e.g., sub-images img_c2 and img_c4) to obtain a second image img_38. However, the number of sub-images shown in FIG. 3D is merely exemplary and is not intended to limit the present invention.

Next, in step S220, the processor 120 performs a stereo matching process on the first image and the second image to generate a disparity map (disparity map) of the first image and the second image. In some embodiments, the processor 120 may perform stereo matching processing on the first image and the second image according to a Block-matching algorithm (Block-matching algorithm) to estimate parallax information and obtain a parallax map. In some embodiments, the processor 120 may perform a stereo matching process on the first image and the second image according to an optical flow algorithm (Optical flow algorithm) to estimate parallax information and obtain a parallax map. In some embodiments, the processor 120 may input the first image and the second image to a trained deep neural network model to obtain the disparity map. In some embodiments, the number of pairs of elements in the disparity map is equal to the resolution of the first image and the second image. For example, assuming that the resolutions of the first image and the second image are 640×480, the disparity map may include disparity information corresponding to 640×480 pixel positions.

In step S230, the processor 120 calculates the number of matches between the plurality of first pixels in the first image and the plurality of second pixels in the second image according to the disparity map. In some embodiments, the disparity map includes a plurality of valid disparity values and a plurality of invalid disparity values, and the number of matches is the number of valid disparity values.

In detail, during the stereo matching process, if a certain first pixel in the first image can be successfully matched to a certain second pixel in the second image, the processor 120 can obtain a corresponding effective disparity value. Conversely, if a certain first pixel in the first image cannot be successfully matched to any second pixel in the second image, the processor 120 may obtain a corresponding invalid disparity value. Therefore, by counting the number of effective disparity values in the disparity map, the number of matches that the plurality of first pixels in the first image successfully match to the plurality of second pixels in the second image can be obtained. In some embodiments, the invalid disparity value in the disparity map will be set to a negative value, and the valid disparity value in the disparity map will be set to an integer value greater than or equal to 0, but the invention is not limited thereto.

In step S240, the processor 120 determines whether the input image is a stereoscopic image according to the matching number. It can be appreciated that if the number of matches is large, the first image and the second image can be determined as the left eye image and the right eye image corresponding to the same shooting scene, so the processor 120 can determine that the input image is a stereoscopic format image conforming to the stereoscopic image format.

In more detail, fig. 4 is a flowchart for determining whether an input image is a stereoscopic format image according to an embodiment of the present invention. Referring to fig. 4, step S240 may be implemented as sub-steps S241-S243. In sub-step S241, the processor 120 determines whether the number of matches meets the matching condition.

In some embodiments, the processor 120 may compare the number of matches with a predetermined threshold to determine whether the number of matches meets the match condition. If the number of matches is greater than the predetermined threshold, the processor 120 may determine that the number of matches meets the match condition. If the number of matches is not greater than the predetermined threshold, the processor 120 may determine that the number of matches does not meet the match condition. The default threshold value may be set according to the image resolution of the input image. That is, different image resolutions will correspond to different preset thresholds.

In some embodiments, the processor 120 may calculate a matching ratio of the number of matches to the number of pixels of the first image, and determine whether the matching ratio is greater than a threshold. That is, the matching ratio is a ratio value of the successfully matched first pixels in the first image to all the first pixels, and may be represented by a percentage or a value less than 1 and greater than 0. If the match ratio is greater than the threshold, the processor 120 may determine that the number of matches meets the match condition. If the match ratio is not greater than the threshold, the processor 120 may determine that the number of matches does not meet the match condition. In the embodiment comparing the matching ratio with the threshold, the same threshold may be applied to different image resolutions.

If the step S241 determines yes, in the substep S242, the processor 120 determines that the input image is a stereoscopic format image conforming to the stereoscopic image format in response to the matching number conforming to the matching condition. In contrast, if the determination in step S241 is negative, in step S243, the processor 120 determines that the input image is not a stereoscopic format image conforming to the stereoscopic image format in response to the matching number not conforming to the matching condition. That is, if the matching number meets the matching condition, the first image and the second image captured from the input image are the left eye image and the right eye image corresponding to the same scene, so that it can be determined that the input image is a stereoscopic format image.

Fig. 5 is a flowchart of a stereoscopic format image detection method according to an embodiment of the present invention. Referring to fig. 5, the manner of the present embodiment is applicable to the electronic device 10 in the above embodiment, and the detailed steps of the present embodiment are described below together with the components of the electronic device 10.

In step S502, the processor 120 divides the input image IMG1 according to the stereoscopic image format to obtain a first image img_l and a second image img_r. In step S504, the processor 120 performs a stereo matching process on the first image img_l and the second image img_r to generate a disparity map d_map of the first image img_l and the second image img_r.

In detail, fig. 6 is a schematic diagram of acquiring a disparity map according to an embodiment of the present invention. The processor 120 takes the first image block B1 with the first target pixel point P1 of img_l on the first image as the center. Next, the processor 120 may acquire the horizontal scan line SL1 according to the Y-axis position of the first target pixel P1 to acquire a plurality of second image blocks (represented by the second image blocks b2_1 to b2_9 in fig. 6) on the second image img_r along the horizontal scan line SL 1. That is, the Y-axis position of the first image block B1 is the same as the Y-axis positions of the second image blocks b2_1 to b2_9, and the size of the first image block B1 is the same as the size of the second image blocks b2_1 to b2_9. It should be noted that the 9 second image blocks b2_1 to b2_9 of fig. 6 are only for exemplary illustration. In some embodiments, the processor 120 may acquire a plurality of second image blocks by taking one pixel as a scanning unit.

Then, the processor 120 calculates a plurality of similarities between the first image block B1 and a plurality of second image blocks on the second image img_r. In some embodiments, these similarities may also be matching costs (matching costs) or values generated based on the matching costs. For example, the processor 120 sequentially calculates absolute differences between the gray-scale values of the first pixels on the first image block B1 and the gray-scale values of the corresponding second pixels on the second image block b2_1, and sums all the absolute differences to obtain the similarity between the first image block B1 and the second image block b2_1. Assuming that the size of the first image block B1 is 91×91, the processor 120 can obtain 91×91 absolute differences.

However, in other embodiments, the processor 120 may also obtain the matching cost corresponding to the plurality of second image blocks based on other calculation methods, such as a square error (Square Difference, SD) algorithm, a pixel-specific measurement (Pixel Dissimilarity Measure, PDM) algorithm, a normalized cross correlation (Normalized Cross Correlation, NCC) algorithm, and the like. In some embodiments, the processor 120 may also perform cost aggregation (cost aggregation) to obtain matching costs corresponding to the plurality of second image blocks.

By repeating the step of performing the similarity calculation along the horizontal scan line SL1, the processor 120 may obtain the similarities corresponding to the plurality of second image blocks, that is, the processor 120 sequentially performs the similarity calculation on the first image and each second image block, so as to obtain the similarities corresponding to the plurality of second image blocks. Then, the processor 120 obtains an effective disparity value or an ineffective disparity value corresponding to the first target pixel point P1 on the disparity map d_map according to the similarities of the plurality of second image blocks corresponding to the horizontal scan line SL1, respectively.

In detail, the processor 120 can determine whether the first image block B1 matches one of the plurality of second image blocks according to the similarity of the plurality of second image blocks respectively corresponding to the horizontal scan line SL 1. In the example of fig. 6, the similarity of the second image blocks on the horizontal scan line SL1 may be shown as a similarity curve C1. The processor 120 can search out a second target image block (i.e. the second image block b2_6 shown in fig. 6) matching the first target image block B1 according to the similarity curve C1. For example, if the processor 120 searches for the maximum similarity of the similarity curve C1 and the maximum similarity is greater than a similarity threshold, the processor 120 may determine that the first image block B1 matches a second image block b2_6 corresponding to the maximum similarity. Alternatively, in some embodiments, if the processor 120 can also search for the smallest difference degree of the plurality of difference degrees and the smallest difference degree is smaller than a difference degree threshold value, the processor 120 can determine that the first image block B1 matches a second image block corresponding to the smallest difference degree. In some embodiments, the degree of difference and the degree of similarity may be reciprocal. In addition, in some embodiments, the processor 120 may also search the second image block matching the first image block B1 by substituting the matching costs into an energy function and optimizing the energy function.

As shown in fig. 6, if the second target image block (i.e., the second image block b2_6) matching the first target image block B1 in the second image block is obtained according to the similarity, the processor 120 obtains the effective parallax value D1 corresponding to the first target pixel point P1 on the parallax map d_map based on the X-axis position X2 of the second target pixel point P2 and the X-axis position X1 of the first target pixel point P1 in the center of the second target image block. On the other hand, if the second target image block matching the first target image block B1 is not obtained according to the similarity, it means that the similarities corresponding to the second image blocks do not meet the predetermined condition, such as that the maximum similarity is not greater than the similarity threshold, the minimum difference is not less than the difference threshold, or the problem of optimizing the energy function is solved. Therefore, if the second target image block matching the first target image block B1 is not obtained according to the similarity, the processor 120 will obtain the invalid disparity value corresponding to the first target pixel point P1 on the disparity map d_map. Alternatively, in some embodiments, the processor 120 may perform denoising processing on the disparity map d_map, and replace the original valid disparity values with invalid disparity values with low reliability.

Referring back to fig. 5, in step S506, the processor 120 calculates the matching number according to the disparity map d_map, and calculates a matching ratio R1 of the matching number to the number of pixels of the first image img_l. That is, the matching ratio R1 is obtained by dividing the number of matches by the number of pixels of the first image img_l. In step S508, the processor 120 determines whether the matching ratio R1 is greater than a threshold value. If so, in step S510, the processor 120 determines that the input image is a stereoscopic format image, and can control the 3D display 20 to display the input image in a corresponding 3D mode. For example, the processor 120 may determine that the input image is a stereoscopic format image. If not, in step S512, the processor 120 determines that the input image is not a stereoscopic format image, and may control the 3D display 20 to display the input image in the 2D mode.

It should be noted that, the processing procedure of the stereoscopic format image detection method executed by at least one processor is not limited to the above embodiment. For example, a part of the above steps (processes) may be omitted, and the steps may be performed in other orders. Any two or more of the above steps may be combined, and a part of the steps may be modified or deleted. Alternatively, other steps may be performed in addition to the above steps.

In summary, in the embodiment of the present invention, whether the input image is a stereoscopic format image conforming to a plurality of different stereoscopic image formats can be effectively distinguished, so that the user experience and application range of the 3D display technology can be improved. After determining that the input image is a stereoscopic image, the 3D display can be automatically switched to an appropriate image playing mode, so that user experience is improved. Or after determining that the input image is a stereoscopic format image, the 3D display can learn the occupied blocks of the left eye image and the right eye image in the input image, so as to facilitate the image processing required by the subsequent 3D display.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.

Claims (16)

1. A stereoscopic format image detection method, suitable for an electronic device, comprising:

dividing an input image according to a stereoscopic image format to obtain a first image and a second image;

performing stereo matching processing on the first image and the second image to generate a parallax image of the first image and the second image;

calculating the matching quantity of a plurality of first pixels in the first image and a plurality of second pixels in the second image according to the parallax map; and

and judging whether the input image is a stereoscopic format image conforming to the stereoscopic image format according to the matching quantity.

2. The stereoscopic format image detection method according to claim 1, wherein the step of judging whether the input image is the stereoscopic format image conforming to the stereoscopic image format according to the matching number comprises:

judging whether the matching quantity meets the matching condition or not;

determining that the input image is the stereoscopic format image conforming to the stereoscopic image format in response to the matching number conforming to the matching condition; and

and determining that the input image is not the stereoscopic format image conforming to the stereoscopic image format in response to the matching quantity not conforming to the matching condition.

3. The stereoscopic format image detection method according to claim 2, wherein the step of judging whether the matching number meets the matching condition comprises:

calculating the matching proportion of the matching quantity to the pixel quantity of the first image; and

judging whether the matching proportion is larger than a threshold value,

if the matching proportion is larger than the threshold value, the matching quantity accords with the matching condition; and if the matching proportion is not greater than the threshold value, the matching quantity does not accord with the matching condition.

4. The stereoscopic format image detection method according to claim 1, wherein the disparity map includes a plurality of valid disparity values and a plurality of invalid disparity values, and the number of matches is the number of valid disparity values.

5. The stereoscopic format image detection method according to claim 1, wherein the step of performing the stereoscopic matching process on the first image and the second image to generate the disparity map of the first image and the second image includes:

taking a first image block by taking a first target pixel point on the first image as a center;

calculating a plurality of similarities between the first image block and a plurality of second image blocks on the second image, wherein a Y-axis position of the first image block is the same as a Y-axis position of the second image block; and

and acquiring an effective parallax value or an ineffective parallax value corresponding to the first target pixel point on the parallax map according to the similarity respectively corresponding to the second image block.

6. The stereoscopic format image detection method according to claim 5, wherein the step of acquiring the effective disparity value or the ineffective disparity value corresponding to the first target pixel point on the disparity map according to the similarities respectively corresponding to the second image block comprises:

if a second target image block matched with the first target image block in the second image block is obtained according to the similarity, obtaining the effective parallax value corresponding to the first target pixel point on the parallax map based on the X-axis position of a second target pixel point in the center of the second target image block and the X-axis position of the first target pixel point; and

and if the second target image block matched with the first target image block in the second image block is not obtained according to the similarity, obtaining the invalid disparity value corresponding to the first target pixel point on the disparity map.

7. The stereoscopic format image detection method according to claim 1, wherein the first image size is the same as the second image size.

8. The stereoscopic format image detection method according to claim 1, wherein the stereoscopic image format includes a side-by-side format, a top-bottom format, a checkerboard pattern format, or an interlaced format.

9. An electronic device, comprising:

a storage device in which a plurality of modules are recorded; and

a processor coupled to the storage device and configured to:

dividing an input image according to a stereoscopic image format to obtain a first image and a second image;

performing stereo matching processing on the first image and the second image to generate a parallax image of the first image and the second image;

calculating the matching quantity of a plurality of first pixels in the first image and a plurality of second pixels in the second image according to the parallax map; and

and judging whether the input image is a stereoscopic format image conforming to the stereoscopic image format according to the matching quantity.

10. The electronic device of claim 9, wherein the processor is further configured to:

judging whether the matching quantity meets the matching condition or not;

determining that the input image is the stereoscopic format image conforming to the stereoscopic image format in response to the matching number conforming to the matching condition; and

and determining that the input image is not the stereoscopic format image conforming to the stereoscopic image format in response to the matching quantity not conforming to the matching condition.

11. The electronic device of claim 10, wherein the processor is further configured to:

calculating the matching proportion of the matching quantity to the pixel quantity of the first image; and

judging whether the matching proportion is larger than a threshold value,

if the matching proportion is larger than the threshold value, the matching quantity accords with the matching condition; and if the matching proportion is not greater than the threshold value, the matching quantity does not accord with the matching condition.

12. The electronic device of claim 9, wherein the disparity map includes a plurality of valid disparity values and a plurality of invalid disparity values, the number of matches being the number of valid disparity values.

13. The electronic device of claim 9, wherein the processor is further configured to:

taking a first image block by taking a first target pixel point on the first image as a center;

calculating a plurality of similarities between the first image block and a plurality of second image blocks on the second image, wherein a Y-axis position of the first image block is the same as a Y-axis position of the second image block; and

and acquiring an effective parallax value or an ineffective parallax value corresponding to the first target pixel point on the parallax map according to the similarity respectively corresponding to the second image block.

14. The electronic device of claim 13, wherein the processor is further configured to:

if a second target image block matched with the first target image block in the second image block is obtained according to the similarity, obtaining the effective parallax value corresponding to the first target pixel point on the parallax map based on the X-axis position of a second target pixel point in the center of the second target image block and the X-axis position of the first target pixel point; and

and if the second target image block matched with the first target image block in the second image block is not obtained according to the similarity, obtaining the invalid disparity value corresponding to the first target pixel point on the disparity map.

15. The electronic device of claim 9, wherein the first image size is the same as the second image size.

16. The electronic device of claim 9, wherein the stereoscopic image format comprises a side-by-side format, a checkerboard format, or an interlaced format.