Electronic apparatus and stereoscopic image display method thereof

Abstract

An electronic apparatus and a stereoscopic image display method thereof are disclosed. The method is adapted to the electronic device including a 3D display and includes the following steps. A display frame including a stream image is obtained. By performing edge detection and line detection, at least one rectangular image area in the display frame is captured. A watermark detection on at least one rectangular image area is performed. In response to a watermark appearing in one of the at least one rectangular image area, a stereoscopic format image is generated based on the display frame and one of the at least one rectangular image area. The stereoscopic display is controlled to operate in a stereoscopic display mode to display the stereoscopic format image, so that image content of the stream image to be displayed with a stereoscopic visual effect.

Description

[Technical Field]

[0001] This disclosure relates to an image processing technique, and more particularly to an electronic device and a method for displaying stereoscopic images thereon. [Previous Technology]

[0002] With the advancement of display technology, stereoscopic displays supporting stereoscopic vision technology have gradually become widespread. Stereoscopic vision technology allows viewers to experience the three-dimensionality of images, such as the three-dimensional features of a person and the depth of field, which traditional 2D images cannot present. The principle of stereoscopic vision technology is to allow the viewer's left eye to see the left-eye image and the viewer's right eye to see the right-eye image, so that the viewer can experience a 3D visual effect. 3D displays can provide left-eye and right-eye images to the viewer's left and right eyes respectively, providing people with an immersive visual experience. It is known that for image content of a specific 3D image format, a 3D display needs to use the corresponding 3D display technology to play it in order to achieve a display result that allows the viewer to experience a 3D visual effect. That is to say, if a 3D display cannot correctly identify the 3D image format of the image content, the 3D display will not be able to successfully provide a display result with a 3D visual effect. [Summary of the Invention]

[0003] This disclosure provides an electronic device and a method for displaying stereoscopic images that can effectively solve the above-mentioned problems.

[0004] An exemplary embodiment of this disclosure provides a stereoscopic image display method applicable to an electronic device including a stereoscopic display and comprising the following steps: Acquiring a display frame including a streaming image. Extracting at least one rectangular image region from the display frame by performing edge detection and line detection. Detecting a watermark on the at least one rectangular image region. Responding to the presence of a watermark in one of the at least one rectangular image region, generating a stereoscopic format image based on the display frame and one of the at least one rectangular image region. Controlling the stereoscopic display to operate in a stereoscopic display mode to display the stereoscopic format image, so that the image content of the streaming image is presented with a stereoscopic visual effect.

[0005] Another exemplary embodiment of this disclosure provides an electronic device including a transceiver, a stereoscopic display, and at least one processor. The transceiver receives a streaming image. The processor is coupled to the transceiver and the stereoscopic display and configured to perform the following operations: Acquire a display frame including a streaming image. Capture at least one rectangular image region in the display frame by performing edge detection and line detection. Detect a watermark on the at least one rectangular image region. In response to the appearance of a watermark in one of the at least one rectangular image region, generate a stereoscopic image based on the display frame and one of the at least one rectangular image region. Control the stereoscopic display to operate in a stereoscopic display mode to display the stereoscopic image, so that the image content of the streaming image is presented with a stereoscopic visual effect.

[0006] Based on the above, in this disclosed embodiment, after acquiring a display frame including a streaming image, at least one rectangular image region in the display frame can be identified through edge detection and line detection. By performing watermark detection on at least one rectangular image region, it can be determined whether each rectangular image region is stereoscopic image content with an embedded watermark. When a certain rectangular image region is stereoscopic image content with an embedded watermark, a stereoscopic format image including a left-eye image and a right-eye image can be generated based on the display frame and the rectangular image region. Therefore, by embedding a watermark in the stereoscopic format image, it is possible to accurately detect that the display frame includes a streaming image conforming to the stereoscopic image format, thereby controlling the stereoscopic display to automatically provide stereoscopic display functionality.

Implementation Method

[0007] Some exemplary embodiments of this disclosure will now be described in detail with reference to the accompanying drawings. Component symbols used in the following description, when appearing in different drawings, are considered to be the same or similar components. These exemplary embodiments are only a part of this disclosure and do not reveal all possible implementations of this disclosure. More precisely, these exemplary embodiments are merely examples of the methods and apparatus within the scope of this patent application.

[0008] FIG1 is a schematic diagram of an electronic device according to an embodiment of the present disclosure. Referring to FIG1, the electronic device 100 can be implemented as, for example, an electronic device with image processing and computing capabilities, such as a notebook computer, tablet computer, personal computer, game console, portable electronic device, desktop computer, or other electronic device. The electronic device 100 includes a transceiver 110, a stereoscopic display 120, a storage device 130, and at least one processor 140.

[0009] Transceiver 110 can transmit and receive signals wirelessly or via a wired connection. The transceiver can also perform operations such as low-noise amplification, impedance matching, mixing, up- or down-frequency conversion, filtering, amplification, and similar operations. Electronic device 100 can receive and transmit data via transceiver 110, such as receiving streaming images from video streams. In some embodiments, electronic device 100 may also include an antenna (not shown) for receiving wireless radio frequency signals.

[0010] The stereoscopic display 120 allows users to experience a stereoscopic visual effect. To enable users to experience 3D visual effects through the stereoscopic display 120, the stereoscopic display 120 can, depending on its hardware specifications and the applied 3D display technology, allow the user's left and right eyes to view image content corresponding to different viewing angles (i.e., left-eye image and right-eye image). In some embodiments, the stereoscopic display 120 can be a naked-eye 3D display, such as a laptop monitor, television, desktop screen, or electronic signage. In some embodiments, the left-eye image and right-eye image can be displayed simultaneously based on stereoscopic image display technology, such as parallax barrier technology, lens technology, or directional backlighting technology.

[0011] On the other hand, the stereoscopic display 120 may include a liquid crystal display (LCD), a light-emitting diode (LED) display, an organic light-emitting diode (OLED) display, or other types of displays, and this disclosure is not limited thereto.

[0012] Storage device 130 is used to temporarily or permanently store data, such as images, instructions, program code, software modules, etc. Specifically, storage device 130 may include volatile storage circuitry. Volatile storage circuitry is used to store data in a volatile manner. For example, volatile storage circuitry may include random access memory (RAM) or similar volatile storage media. Alternatively, storage device 130 may include non-volatile storage circuitry. Non-volatile storage circuitry is used to store data in a non-volatile manner. For example, non-volatile storage circuitry may include read-only memory (ROM), solid-state drive (SSD), and / or traditional hard disk drive (HDD) or similar non-volatile storage media. The number of storage devices 130 may be one or more, and this disclosure is not limited thereto.

[0013] Processor 140 connects to transceiver 110, stereoscopic display 120, and storage device 130, and is responsible for all or part of the operation of electronic device 100. For example, processor 140 may include a central processing unit (CPU), a graphics processing unit (GPU), or other programmable general-purpose or special-purpose microprocessor, digital signal processor (DSP), programmable controller, application-specific integrated circuit (ASIC), programmable logic device (PLD), or other similar device or combination of these devices. The number of processors 140 may be one or more, and this disclosure does not limit this.

[0014] Figure 2 is a schematic diagram of a stereoscopic display according to an embodiment of the present disclosure. Referring to Figure 2, in some embodiments, the stereoscopic display 120 may be a naked-eye stereoscopic display, which can provide different images to the left and right eyes through the principle of lens refraction, allowing the viewer to experience a stereoscopic display effect. The stereoscopic display 120 may include a display panel 121 and a lens layer 122. The lens layer 122 is disposed above the display panel 121, and the viewer can see the image content provided by the display panel 121 through the lens layer 122. The stereoscopic display 120 can place the pixels of the left-eye image and the pixels of the right-eye image at the corresponding pixel positions of the display panel 121, respectively. Through the refraction of light, the lens layer 122 refracts different display content (i.e., the left-eye image and the right-eye image) to different positions in space, so that the left and right eyes can receive two different images with parallax, respectively. As is known, in order to place the pixels of the left-eye image and the right-eye image at the corresponding pixel positions on the display panel 121, the left-eye image and the right-eye image need to undergo image weaving processing to produce a weaving frame in which the pixels of the left-eye image and the pixels of the right-eye image are arranged alternately.

[0015] FIG3 is a flowchart of a stereoscopic image display method according to an embodiment of the present disclosure. Referring to FIG3, the operation flow of this embodiment is applicable to the electronic device 100 in the above embodiment. The detailed steps of this embodiment are described below with reference to the various components in the electronic device 100.

[0016] In step S310, the processor 140 acquires a display frame including a streaming image. Specifically, the processor 140 can receive a video stream including the streaming image through the transceiver 110. That is, the processor 140 can receive the streaming image through the transceiver 110 and generate a display frame including the streaming image. In some embodiments, the processor 140 can use a screenshot function to acquire the display frame including the streaming image. In some embodiments, the streaming image may originate from a video conferencing program, a multimedia player, or a browser program's video stream. In some embodiments, when the processor 140 executes video conferencing software, the processor 140 can receive streaming images provided by conference participants through the transceiver 110 and generate a display frame including the video conferencing software's window interface and the streaming image.

[0017] In some embodiments, the processor 140 may capture display frames through an application programming interface (API) provided by the operating system. For example, the processor 140 may use screen capture technologies such as the "Desktop Duplication API" or "DirectX Graphics Infrastructure (DXGI)" of the Windows operating system to acquire display frames, but is not limited to these.

[0018] In this embodiment of the disclosure, an image conforming to a stereoscopic image format can be embedded with a watermark to generate a streaming image. The watermark can be an invisible watermark. Therefore, the processor 140 can determine whether the currently displayed streaming image conforms to a stereoscopic image format based on the watermark detection result. The stereoscopic image format is, for example, a side-by-side (SBS) image format, which is not limited in this disclosure. The operation of embedding a watermark into a stereoscopic format image can be achieved by post-processing an image conforming to a stereoscopic image format. Alternatively, a specially designed stereoscopic image capturing device can be used to directly output a stereoscopic format image with an embedded watermark.

[0019] For example, Figure 4 is a schematic diagram of embedding a watermark according to an embodiment of the present disclosure. Referring to Figure 4, the original image Imgr_1, conforming to a side-by-side image format, has a left-eye image ImgL1 and a right-eye image ImgR1. After watermark embedding processing, an invisible watermark can be embedded in the original image Imgr_1 to generate a streaming image Imgs_1. The streaming image Imgs_1 includes a left-eye image ImgL2 and a right-eye image ImgR2. In some embodiments, the invisible watermark can be embedded through spatial domain embedding processing or frequency domain embedding processing. In some embodiments, the invisible watermark can be embedded through a deep learning network model. The aforementioned deep learning network model can be a generative adversarial network (GAN) model, such as the Robust Invisible Video Watermarking with Attention-Guided Generative Adversarial Network (RivaGAN) model. Therefore, when the processor 140 receives the streaming image Imgs_1 through the transceiver 110 and generates a display frame including the streaming image Imgs_1, the processor 140 can identify the watermark in the display frame by performing watermark detection on a specific rectangular image area in the display frame.

[0020] Returning to Figure 3, in step S320, by performing edge detection and line detection, the processor 140 captures at least one rectangular image region in the display frame. Furthermore, the streaming image will be displayed within a rectangular image region in the display frame, therefore the processor 140 can first identify multiple rectangular image regions in the display frame. That is, the processor 140 can use edge detection and line detection to find the streaming image in the display frame. In step S330, the processor 140 performs a watermark detection on at least one rectangular image region. That is, the processor 140 can sequentially perform watermark detection on each rectangular image region. In step S340, the processor 140 determines whether a watermark appears in one of the at least one rectangular image regions.

[0021] In detail, the display frame acquired based on screen capture technology may include streaming images and other image content (such as window operation interfaces, etc.), and image content unrelated to the presence of a watermark may affect the accuracy and efficiency of watermark detection. Therefore, in this disclosed embodiment, the processor 140 may first identify one or more rectangular image regions in the display frame through edge detection and line detection, and the streaming image is displayed in one of these rectangular image regions. Then, the processor 140 may perform watermark detection on these rectangular image regions, thereby determining whether the display frame includes a streaming image with a watermark and obtaining the location of the streaming image with a watermark.

[0022] In some embodiments, the processor 140 can detect an invisible watermark in at least one rectangular image region using a deep learning model. That is, the processor 140 can input each rectangular image region into a deep learning model, which can attempt to extract the watermark from each rectangular image region. When the deep learning model cannot find the watermark in a certain rectangular image region, it can output a preset indicator or value representing that the watermark does not exist. When the deep learning model can find the watermark in a certain rectangular image region, it can output the binary code of the watermark. The deep learning model is, for example, the RivaGAN model, but is not limited to this.

[0023] It is worth mentioning that if the entire display frame is directly input into the deep learning model, even if a watermark is embedded in the streaming image within the display frame, the processor 140 may not be able to correctly detect the presence of the watermark using the deep learning model. This is because the display frame may also include other image content unrelated to the streaming image, and this other image content is also unrelated to the deep learning model's watermark embedding process. Therefore, the deep learning model may not be able to correctly detect the presence of the watermark from the display frame. Therefore, this disclosure improves the accuracy of watermark detection by identifying multiple rectangular image regions.

[0024] If step S340 determines that it is yes, it means that the streaming image conforms to the stereoscopic image format. In step S350, in response to a watermark appearing in at least one of the rectangular image areas, the processor 140 generates a stereoscopic image based on the displayed frame and one of the at least one rectangular image area. This stereoscopic image is a side-by-side image including a first-view image and a second-view image. The first-view image may be a left-eye image, and the second-view image may be a right-eye image. Alternatively, the first-view image may be a right-eye image, and the second-view image may be a left-eye image.

[0025] In detail, since the user may zoom or move the application window, the size and position of the streaming image within the application window in the display frame are variable. In this disclosed embodiment, in response to the movement or zooming of the application window, the rectangular image area with the watermark can also move and zoom accordingly. Therefore, based on the range defined by the rectangular image area with the watermark, the processor 140 can obtain the image occupancy range of the streaming image conforming to the stereoscopic image format in the display frame.

[0026] Therefore, the processor 140 can generate a left-eye image and a right-eye image of a stereoscopic image based on the two-dimensional background block in the display frame and the rectangular image area with the watermark. Specifically, the left-eye image of the stereoscopic image may include the two-dimensional background block in the display frame and the left-eye image of the streaming image. The right-eye image of the stereoscopic image may include the two-dimensional background block in the display frame and the right-eye image of the streaming image. In other words, the stereoscopic image simultaneously includes 3D image content with parallax and a two-dimensional background without parallax.

[0027] In step S360, the processor 140 controls the stereoscopic display 120 to operate in stereoscopic display mode to display a stereoscopic format image, so that the image content of the streaming image is presented with a stereoscopic visual effect. Specifically, when the stereoscopic display 120 is a naked-eye stereoscopic display, the processor 140 can perform image weaving processing on the stereoscopic format image (e.g., an SBS image) to obtain a woven image. This image weaving processing arranges the pixels of the left-eye image and the right-eye image of the stereoscopic format image alternately within the woven frame. Then, when the stereoscopic display 120 operates in stereoscopic display mode, the display panel 121 of the stereoscopic display 120 will display the woven image, and the refraction function of the lens layer 122 of the stereoscopic display 120 is enabled, allowing the viewer to experience a stereoscopic visual effect.

[0028] For example, in the case where the processor 140 is running video conferencing software, in response to the appearance of a watermark in a rectangular image area in the display frame, the stereoscopic display 120 can enable the stereoscopic display function and display the stereoscopic streaming content provided by the meeting participants and the window operation interface of the video conferencing software. Therefore, the user can experience a stereoscopic visual effect.

[0029] On the other hand, if step S340 determines otherwise, it means that the streaming image does not conform to the stereoscopic image format. In step S370, in response to the absence of a watermark in at least one rectangular image area, the processor 140 controls the stereoscopic display 120 to operate in two-dimensional display mode and display the display frame. In some embodiments, when the stereoscopic display 120, which is a naked-eye stereoscopic display, operates in two-dimensional display mode and does not provide stereoscopic display functionality, the display panel 121 of the stereoscopic display 120 will output the display frame, and the refraction function of the lens layer 122 of the stereoscopic display 120 is disabled.

[0030] For example, in the case where the processor 140 is running video conferencing software, if the watermark does not appear in any rectangular image area of ​​the display frame, the stereoscopic display 120 may disable the stereoscopic display function and display a display frame including the streaming image and the window operation interface of the video conferencing software.

[0031] FIG5 is a flowchart of capturing at least one rectangular image region according to an embodiment of the present disclosure. Referring to FIG5, the operation flow of this embodiment is applicable to the electronic device 100 in the above embodiment. The detailed steps of this embodiment will be described below with reference to the various components in the electronic device 100. To clearly explain the principle of this embodiment, FIG6 will be used as an aid in the following description. FIG6 is a schematic diagram of capturing at least one rectangular image region according to an embodiment of the present disclosure.

[0032] In step S510, the processor 140 performs a contrast adjustment process on the display frame Img61. The processor 140 can improve the contrast of the display frame Img61, making the brightness differences between different areas in the display frame Img61 more obvious, thereby making the edges in the display frame Img61 more prominent.

[0033] In step S520, the processor 140 performs a Gaussian blur on the display frame Img61 that has undergone contrast adjustment processing to reduce noise and smooth the edges.

[0034] In step S530, the processor 140 performs edge detection on the display frame Img61, which has undergone contrast adjustment and Gaussian blur processing, to obtain an edge image Img62. The edge image Img62 may be a binary image composed of edge pixels. Edge detection may be, for example, Canny edge detection, but is not limited to this.

[0035] In step S540, the processor 140 performs line detection on the edge image Img62, and extracts at least one rectangular image region from the display frame Img61 based on multiple lines L61 to L65. In this embodiment, step S540 can be implemented as steps S541 to S543.

[0036] In step S541, the processor 140 performs line detection on the edge image Img62 to obtain multiple lines L61 to L65 from the edge image. In some embodiments, the multiple lines L61 to L65 include multiple vertical lines and multiple horizontal lines. In some embodiments, the processor 140 may perform line detection based on the Hough transform procedure. The processor 140 may perform edge detection to obtain multiple edges in the edge image Img62, and filter out multiple vertical lines and multiple horizontal lines with lengths greater than a length threshold from these edges. However, regarding line detection, the Hough transform procedure or other line detection algorithms well known to those skilled in the art can be applied, without specific limitations.

[0037] In step S542, the processor 140 filters at least one target rectangle contour RCT6 from at least one candidate rectangle contour formed by multiple straight lines based on a rectangle size constraint and a rectangle proportion constraint. The processor 140 can determine whether multiple straight lines L61 to L65 can form a candidate rectangle contour. Further, the processor 140 can identify at least one candidate rectangle contour formed by a portion of the straight lines based on the slope, intersection point, length, and other straight line information of the straight lines L61 to L65. For example, the processor 140 can identify a candidate rectangle contour formed by straight lines L64, L65, L61, and L62. The processor 140 can identify another candidate rectangle contour formed by straight lines L64, L65, L63, and L62.

[0038] Next, the processor 140 can determine whether these candidate rectangular outlines meet the rectangle size limit. For example, the processor 140 can determine whether the area of ​​these candidate rectangular outlines is greater than the lower limit of the rectangle area. The processor 140 can determine whether the area of ​​these candidate rectangular outlines is less than the upper limit of the rectangle area. Alternatively, the processor 140 can determine whether these candidate rectangular outlines meet the rectangle ratio limit. For example, the processor 140 can determine whether the aspect ratio of these candidate rectangular outlines is within a preset range. Based on this, through filtering by the rectangle size limit and the rectangle ratio limit, the processor 140 can filter at least one target rectangular outline RCT6 from at least one candidate rectangular outline.

[0039] In step S543, the processor 140 extracts at least one rectangular image region Re_z1 from the display frame Img61 based on at least one target rectangular outline RCT6. However, Figure 6 is only used to illustrate the detection principle of rectangular image regions. The number and position of lines, and the number and position of rectangular image regions, depend on the actual content of the display frame.

[0040] FIG7 is a flowchart of generating a stereoscopic image according to an embodiment of the present disclosure. Referring to FIG7, the operation flow of this embodiment applies to the electronic device 100 in the above embodiment. The detailed steps of this embodiment will be described below with reference to the various components in the electronic device 100. To clearly explain the principle of this embodiment, FIG8 will be used as an aid in the following description. FIG8 is a schematic diagram of generating a stereoscopic image and weaving a frame according to an embodiment of the present disclosure. Please refer to FIG7 and FIG8 together.

[0041] In step S710, the processor 140 divides the display frame F81 into at least one rectangular image region (i.e., rectangular image region Z1) and a two-dimensional background image block Z2. That is, after the processor 140 detects the presence of the watermark in the rectangular image region Z1, the processor 140 divides the display frame F81 into the rectangular image region Z1 with the watermark and the two-dimensional background image block Z2. The rectangular image region Z1 includes a streaming image that conforms to a stereoscopic image format and includes a first-view image L_1 (i.e., the left-eye image) and a second-view image R_1 (i.e., the right-eye image).

[0042] In step S720, the processor 140 combines the first-view image L_1 of the streaming image in at least one of the rectangular image regions (i.e., rectangular image region Z1) with the two-dimensional background image block Z2 to form a first-view image L_2 of the stereoscopic format image Imgf1. The at least one of the rectangular image regions (i.e., rectangular image region Z1) includes a streaming image conforming to a stereoscopic image format. Specifically, the processor 140 can perform image scaling processing on the first-view image L_1 of the streaming image according to the display block size of the rectangular image region Z1. The processor 140 can synthesize the scaled first-view image L_1 and the two-dimensional background image block Z2 according to the display position of the rectangular image region Z1 to generate the first-view image L_2.

[0043] In step S730, the processor 140 combines the second-view image R_1 of the streaming image in at least one of the rectangular image regions (i.e., the rectangular image region Z1) with the two-dimensional background image block Z2 to form a second-view image R_2 of the stereo format image Imgf1. The method of generating the second-view image R_2 is the same as the method of generating the first-view image L_2, and will not be described again here.

[0044] In some embodiments, when the stereoscopic display 120 is a naked-view stereoscopic display, the processor 140 may perform image weaving processing on the stereoscopic format image Imgf1 to generate a woven image frame WF1. In this case, when the stereoscopic display 120 displays the woven image frame WF1, the viewer can see stereoscopic streaming content with a stereoscopic visual effect.

[0045] Figure 9 is a schematic diagram of a scenario in which the image content of a streaming image is presented with a stereoscopic visual effect according to an embodiment of the present disclosure. Referring to Figure 9, the electronic device 100 can execute a conference software program to display a display frame F91. The display frame F91 includes a streaming image Img91 and a window operation interface, and the streaming image Img91 conforming to the SBS format has an embedded watermark. Therefore, after detecting that the streaming image Img91 has a watermark, the electronic device 100 can switch to a stereoscopic display mode to display the display frame F92, so that the image content of the streaming image Img91 is presented with a stereoscopic visual effect.

[0046] In summary, in this disclosed embodiment, if a watermark appears in a rectangular image area of ​​a display frame, it can be determined that the display frame includes a stereoscopic streaming image conforming to a stereoscopic image format. Furthermore, the image range of the streaming image conforming to the stereoscopic image format can be determined based on the rectangular image area where the watermark is detected, thus distinguishing between the 3D content image area and the two-dimensional background area in the display frame. Subsequently, the display frame can be converted into a stereoscopic format image including left-eye and right-eye images, and the stereoscopic display can be controlled to operate in stereoscopic display mode to display the stereoscopic format image. Therefore, by embedding a watermark in the stereoscopic format image, it is possible to accurately detect that the display frame includes a streaming image conforming to a stereoscopic image format, thereby controlling the stereoscopic display to automatically provide stereoscopic display functionality. In addition, since watermark detection is performed on each rectangular image area, the accuracy and efficiency of watermark detection can be improved. [Simplified Explanation of the Diagram]

[0047] FIG1 is a schematic diagram of an electronic device according to an embodiment of the present disclosure. FIG2 is a schematic diagram of a stereoscopic display according to an embodiment of the present disclosure. FIG3 is a flowchart of a stereoscopic image display method according to an embodiment of the present disclosure. FIG4 is a schematic diagram of embedding a watermark according to an embodiment of the present disclosure. FIG5 is a flowchart of capturing at least one rectangular image region according to an embodiment of the present disclosure. FIG6 is a schematic diagram of capturing at least one rectangular image region according to an embodiment of the present disclosure. FIG7 is a flowchart of generating a stereoscopic format image according to an embodiment of the present disclosure. FIG8 is a schematic diagram of generating a stereoscopic format image and weaving a frame according to an embodiment of the present disclosure. FIG9 is a schematic diagram of a scenario in which the image content of a streaming image is presented with a stereoscopic visual effect according to an embodiment of the present disclosure.

Claims

1. A method for displaying stereoscopic images, applicable to electronic devices including a stereoscopic display, and comprising: The method involves: acquiring a display frame comprising a streaming image; extracting at least one rectangular image region from the display frame by performing edge detection and line detection; detecting a watermark in the at least one rectangular image region; generating a stereoscopic image based on the display frame and the at least one rectangular image region in response to the appearance of a watermark in one of the at least one rectangular image regions; and controlling the stereoscopic display to operate in a stereoscopic display mode to display the stereoscopic image, so that the image content of the streaming image is presented with a stereoscopic visual effect.

2. The stereoscopic image display method as described in claim 1, further comprising: In response to the absence of the watermark in the at least one rectangular image area, the stereoscopic display is controlled to operate in two-dimensional display mode to display the display frame.

3. The stereoscopic image display method as claimed in claim 1, wherein the step of capturing the at least one rectangular image region in the display frame by performing the edge detection and the line detection includes: The edge detection is performed on the displayed image frame to obtain an edge image; And perform the line detection on the edge image, and extract the at least one rectangular image region in the display frame based on multiple lines.

4. The stereoscopic image display method as claimed in claim 3, wherein the step of performing the line detection on the edge image and extracting the at least one rectangular image region in the display frame based on the plurality of lines includes: Perform the line detection on the edge image to obtain multiple straight lines from the edge image; Based on a rectangle size constraint and a rectangle ratio constraint, at least one target rectangle contour is selected from at least one candidate rectangle contour formed by the plurality of straight lines; and the at least one rectangular image region is extracted from the display frame based on the at least one target rectangle contour.

5. The stereoscopic image display method as described in claim 4, wherein the plurality of straight lines includes a plurality of vertical straight lines and a plurality of horizontal straight lines.

6. The stereoscopic image display method as claimed in claim 3, wherein before the step of performing the edge detection on the display frame to obtain the edge image, the method further comprises: Perform a contrast adjustment process on the displayed image frame; And a Gaussian blur is applied to the displayed image frame.

7. The stereoscopic image display method as claimed in claim 1, wherein the step of generating the stereoscopic format image based on the display frame and one of the at least one rectangular image regions in response to the appearance of the watermark includes: The display frame is divided into at least one rectangular image region and a two-dimensional background image block, wherein the at least one rectangular image region includes the streaming image conforming to a stereoscopic image format; a first-view image of the streaming image in the at least one rectangular image region and the two-dimensional background image block are combined to form a first-view image of the stereoscopic format image; and a second-view image of the streaming image in the at least one rectangular image region and the two-dimensional background image block are combined to form a second-view image of the stereoscopic format image.

8. The stereoscopic image display method as described in claim 7, wherein the stereoscopic image format includes a side-by-side format.

9. The stereoscopic image display method as described in claim 1, wherein acquiring the display frame including the streaming image comprises: Use a screenshot function to capture the display frame including the streaming image.

10. The stereoscopic image display method as claimed in claim 1, wherein the step of detecting the watermark in the at least one rectangular image region includes: An invisible watermark in the at least one rectangular image region is detected using a deep learning model.

11. An electronic device comprising: A transceiver used to receive a stream of images; A 3D display; The system includes at least one processor coupled to the transceiver and the stereo display, and configured to: acquire a display frame including the streaming image; extract at least one rectangular image region from the display frame by performing edge detection and line detection; perform a watermark detection on the at least one rectangular image region; generate a stereo format image based on the display frame and the at least one rectangular image region in response to the appearance of a watermark in one of the at least one rectangular image regions; and control the stereo display to operate in a stereo display mode to display the stereo format image so that the image content of the streaming image is presented with a stereo visual effect.

Images