Method and device for acquiring non-shielded area of ​​target detection

Abstract

The present invention discloses a method, device, electronic device and storage medium for obtaining a non-shielded area for target detection. The target detection method includes the following steps: obtaining a first image frame of a first video captured by a camera, and obtaining a second image frame of a second video of a display device input source, wherein the content captured by the camera includes a display device, and the display device is playing the second image frame; processing the first image frame to obtain a playback area image of the display device in the first image frame; performing a first comparison between the playback area image and the second image frame and obtaining a first comparison result, and obtaining a first non-shielded area in the display device area in the first image frame based on the first comparison result. This method is aimed at the scenario where a teacher or lecturer performs target detection while explaining content in front of a screen, and performs target detection with high precision and low interference.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence vision, and more specifically, to a method, device, electronic device and storage medium for acquiring a non-shielded area for target detection. Background Art

[0002] Artificial intelligence visual object detection is widely used in various fields and scenarios, such as teacher detection or student detection in distance education, speaker detection in remote conferences, etc. At present, whether it is school teaching or remote conferences, teachers or speakers like to use multimedia tools to explain their content in front of the screen.

[0003] However, when the teacher or lecturer is explaining his or her content in front of the screen, the content displayed on the screen will more or less interfere with the AI ​​visual target detection (such as Figure 2a As shown, it is possible to detect both the teacher and Du Fu during target detection). At present, in order to avoid interference from the screen output content, a specific area in the screen is usually manually calibrated as a shielding area. When acquiring the image, the content of the area is set to zero to avoid interference, but this will cause the loss of useful information in this area in the usage scenario. When the target person walks into the shielding area, it is impossible to continue the target detection, face recognition and other artificial intelligence visual recognition operations. Summary of the invention

[0004] In order to overcome at least one of the defects of the prior art, the present invention provides a method, device, electronic device and storage medium for acquiring a non-shielded area for target detection. The technical solution adopted by the present invention is as follows.

[0005] In a first aspect, the present invention provides a method for acquiring a non-shielded area for target detection, comprising the steps of:

[0006] Acquire a first image frame of a first video captured by a camera, and acquire a second image frame of a second video input from a display device, wherein the content captured by the camera includes a display device, and the display device is playing the second image frame;

[0007] Processing the first image frame to obtain a playback area of ​​a display device within the first image frame;

[0008] A first comparison is performed on the image data of the playback area and the image data of the second image frame to obtain a first comparison result, and based on the first comparison result, a first non-shielded area in the display device area in the first image frame is obtained.

[0009] In one implementation, the process of obtaining the first non-shielded area in the display device area in the first image frame based on the first comparison result includes the steps of:

[0010] Obtaining a first comparison result;

[0011] Obtaining a preliminary non-shielded area according to the first comparison result;

[0012] Obtaining a first minimum circumscribed rectangle based on the preliminary non-shielded area;

[0013] The area of ​​the first minimum circumscribed rectangle is used as the first non-shielding area.

[0014] In one implementation, the process of obtaining the first non-shielded area in the display device area in the first image frame based on the first comparison result includes the steps of:

[0015] Obtaining a first comparison result;

[0016] Obtaining a preliminary non-shielded area according to the first comparison result;

[0017] Obtaining a first minimum circumscribed rectangle based on the preliminary non-shielded area;

[0018] Extending the bottom edge of the first minimum circumscribed rectangle to the bottom edge of the playback area to obtain a second minimum circumscribed rectangle;

[0019] The area of ​​the second minimum circumscribed rectangle is used as the first non-shielding area.

[0020] In one embodiment, the steps are further included:

[0021] When more than one playback area is obtained, performing a second comparison on the image data of all the playback areas and the image data of the second image frame to obtain a second comparison result;

[0022] Based on the second comparison result, the image data of the playback area used in performing the first comparison is determined.

[0023] In one implementation, the process of processing the first image frame to obtain the playback area of ​​the display device in the first image frame includes the steps of:

[0024] Processing the first image frame to obtain a display device area within the first image frame;

[0025] A playback area of ​​the display device is extracted from the display device area.

[0026] In one embodiment, the steps are further included:

[0027] Processing the first image frame to obtain a second non-shielded area in the first image frame, wherein the second non-shielded area is an area outside a playback area of ​​a display device in the first image frame;

[0028] A non-shielding area of ​​a first image frame is obtained based on the first non-shielding area and the second non-shielding area.

[0029] In one embodiment, the steps are further included:

[0030] Obtaining a time difference between a second video played by a display device in the first video and a second video obtained from an input source of the display device;

[0031] The first image frame and the second image frame are acquired according to the time difference.

[0032] In a second aspect, the present invention provides a device for acquiring a non-shielded area for target detection, comprising:

[0033] an acquisition module, configured to acquire a first image frame of a first video captured by a camera, and acquire a second image frame of a second video input from a display device, wherein the content captured by the camera includes a display device, and the display device is playing the second image frame;

[0034] A processing module, used for processing the first image frame to obtain a playback area of ​​a display device within the first image frame;

[0035] The analysis module is used to perform a first comparison between the image data of the playback area and the image data of the second image frame and obtain a first comparison result, and based on the first comparison result, obtain a first non-shielded area in the display device area in the first image frame.

[0036] In a third aspect, the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-mentioned methods when executing the program.

[0037] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the method of any of the above-mentioned embodiments when the program is executed by a processor.

[0038] In the present invention, for the scenario where target detection is performed while a teacher or lecturer is explaining content in front of a screen, the video in the input source of the display device is obtained and compared with the display device playback area in the video shot with the display device, so as to separate the background playback picture and the foreground non-shielded area where target detection is required, thereby solving the technical problems of large interference and inaccurate detection in the prior art, so that the teacher or lecturer can perform target detection with high precision while explaining content in front of the screen. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flow chart of the first embodiment.

[0040] Figure 2a It is a schematic diagram of the overall screen of the first video of Example 1.

[0041] Figure 2b It is a schematic diagram of the screen of the second video of Example 1.

[0042] Figure 3 It is a schematic diagram of a screen of the first video of Example 1.

[0043] Figure 4a This is another schematic diagram of the first video of Example 1.

[0044] Figure 4b This is another screen diagram of the first video of Example 1.

[0045] Figure 5 It is a structural diagram of the second embodiment. DETAILED DESCRIPTION

[0046] The exemplary embodiments disclosed in the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments disclosed in the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0047] It should be noted that the terms "first\second\..." involved in the embodiments of the present invention are only used to distinguish similar objects, and do not represent a specific order for the objects. It is understandable that the specific order or sequence of "first\second\..." can be interchanged where permitted. It should be understood that the objects distinguished by "first\second\..." can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0048] Embodiment 1

[0049] See also Figure 1 , Figure 1 1 is a flow chart of a method for acquiring a non-shielded area for target detection provided in the first embodiment of the present invention, the method comprising step S110, step S120, and step S130. It should be noted that step S110, step S120, and step S130 are merely reference numerals for the purpose of clearly explaining the embodiment and the appendix. Figure 1 The corresponding relationship does not represent a limitation on the order of the steps of the method in this embodiment.

[0050] Step S110, obtaining a first image frame of a first video captured by a camera, and obtaining a second image frame of a second video input from a display device, wherein the content captured by the camera includes a display device, and the display device is playing the second image frame.

[0051] like Figure 2a As shown, Figure 2a is the first video captured by the camera. The content captured in the first video includes display device 1 (of course, it also includes the content being played on the display device). In this embodiment, display device 1 is a screen used by the teacher for teaching. Take the image frame at time t1 in the first video. The image frame at time t1 is the first video frame. Obtain the second video played on the second device from the input source of the display device, and obtain the image frame at time t2 (such as Figure 2b As shown in the figure, the image frame at time t2 is the second video frame. Since the video in the display device captured by the camera has a time delay relative to the acquired second video, the time delay must be measured in advance, that is, the correspondence between time t1 of the first video and time t2 of the second video must be determined to ensure that the content played by the display device in the image frame at time t1 of the first video is the second image frame.

[0052] Step S120: Process the first image frame to obtain a playback area of ​​the display device within the first image frame.

[0053] like Figure 2a As shown, Figure 2a is the first image frame in the first video, and the first image frame is processed to obtain Figure 3 The playback area of ​​the display device within the first image frame shown.

[0054] It should be noted that what is processed in this step is the playback area of ​​the display device. In addition to the content being played on the display device, the playback area also includes people or objects that block the display device, such as Figure 3 The teacher in.

[0055] This method does not limit how to obtain the playback area of ​​the display device in the image frame. For example, the camera shot can be processed by a trained target detection network for screen categories, and the position coordinates of the screen in the picture can be output after calculation by a convolutional neural network, so as to obtain the playback area. For another example, the four corners or borders of the physical display device can be marked in advance, and the playback area in the video frame can be obtained by finding the marked points. For another example, the second image frame can be used to search the image pyramid sliding window to retrieve the playback area in the first image frame.

[0056] Step S130 , performing a first comparison on the image data of the playback area and the image data of the second image frame to obtain a first comparison result, and based on the first comparison result, obtaining a first non-shielded area in the display device area in the first image frame.

[0057] Since the picture being played by the display device in the first image frame is the same as the content of the second image frame obtained from the second video stream, the teacher as the foreground and the playing picture as the background can be separated by comparing the image data of the playback area with the image data of the second image frame.

[0058] For example Figure 3 The playback area picture shown and Figure 2b The second image frame shown is subjected to a first comparison and a first comparison result is obtained. Of course, before the comparison, the image data of the playback area and the image data of the second image frame can be resampled to the same size to facilitate the comparison. The first comparison result is actually a set of comparison results of the pixels at the same position in the two images. For example, the playback area image and the second image frame are simultaneously converted into grayscale images, the playback area image is subtracted from the image of the second image frame output by the screen source, and a difference image is obtained. The difference threshold val_thres is set based on experience, and the difference image of the processing area is filtered, and the pixel points greater than val_thres are set to 1, which are considered to be foreground points, and the pixel points less than val_thres are set to 0, which are considered to be background points, and a mask matrix is ​​obtained, which is the first comparison result.

[0059] Of course, those skilled in the art may also use other methods to obtain a set of comparison results of pixels at the same position in two images.

[0060] After obtaining the first comparison result, the first comparison result is conventionally sorted to obtain a non-shielded area. For example, a closing operation is performed on the filtered difference image to filter out scattered foreground points, and then the area of ​​the foreground points is connected according to the 8-connected domain, and the area with the largest area of ​​the connected area is counted, and the area with the largest area of ​​the connected area of ​​the foreground point is used as the non-shielded area.

[0061] Of course, the shape of the largest area may not be a regular shape, which is not conducive to subsequent target detection, so the irregularly shaped largest area may also be trimmed, and the trimmed area is output as a non-shielded area.

[0062] In this method, for the scenario where target detection is performed while a teacher or lecturer is explaining content in front of the screen, the video in the input source of the display device is obtained, and compared with the display device playback area in the video shot with the display device, the background playback picture and the foreground non-shielded area where target detection is required are separated, thereby solving the technical problems of large interference and inaccurate detection in the prior art, so that the teacher or lecturer can also perform target detection with high precision when explaining content in front of the screen.

[0063] In one implementation, the process of obtaining the first non-shielded area in the display device area in the first image frame based on the first comparison result includes: step S131, step S132 and step S133.

[0064] Step S131, obtaining a first comparison result;

[0065] Step S132, obtaining a preliminary non-shielded area according to the first comparison result;

[0066] Step S133: obtaining a first minimum circumscribed rectangle based on the preliminary non-shielded area.

[0067] This embodiment is aimed at the aforementioned process of trimming the irregularly shaped largest area, which may not be a regular shape and is not conducive to subsequent target detection. Steps S131 and S132 have been introduced before, and will not be repeated here. The preliminary non-shielded area in step S132 is the largest area of ​​the connected area of ​​the foreground point mentioned before. Since target detection is generally obtained using a rectangular frame, the corresponding first minimum bounding rectangle is obtained based on the preliminary non-shielded area in step S133, and the area of ​​the first minimum bounding rectangle is used as the first non-shielded area.

[0068] In this embodiment, the non-shielded area is trimmed to obtain a non-shielded area that is beneficial for subsequent target detection.

[0069] In one implementation, the process of obtaining the first non-shielded area in the display device area in the first image frame based on the first comparison result further includes: step S134 and step S135.

[0070] Step S134, extending the bottom edge of the first minimum bounding rectangle to the bottom edge of the playback area image to obtain a second minimum bounding rectangle;

[0071] Step S135: Using the area of ​​the second minimum circumscribed rectangle as the first non-shielding area.

[0072] Normally, the teacher's body will extend to the bottom of the picture in the playback area. Figure 4a As shown in , the first minimum bounding rectangle also naturally extends to the bottom of the playback area image. However, sometimes the color of the teacher's clothes may be similar to the color of the content being played on the screen, resulting in the teacher's body being partially hidden. Figure 4b As shown in FIG. 1 , the first minimum bounding rectangle does not extend to the bottom of the play area image, so the first minimum bounding rectangle cannot really frame the teacher. In order to avoid the above situation, steps S134 and S135 forcibly extend the bottom edge of the first minimum bounding rectangle to the bottom edge of the play area image to obtain a second minimum bounding rectangle. Figure 4b The minimum enclosing rectangle is forced to expand Figure 4a The minimum circumscribed rectangle of the first shielding area is used as the area of ​​the second minimum circumscribed rectangle.

[0073] In this implementation, the previous implementation is optimized, and a non-shielded area that is more suitable for subsequent target detection is adjusted according to actual conditions.

[0074] In one embodiment, the method for acquiring the non-shielded area for target detection further includes: step S140 and step S150.

[0075] Step S140, when more than one playback area is obtained, performing a second comparison on the image data of all the playback areas and the image data of the second image frame to obtain a second comparison result;

[0076] Step S150: determining the image data of the playback area in the first comparison based on the second comparison result.

[0077] In the process of step S120, there may be a situation where there are multiple results of the screen position information, and in this case, more than one play area will be generated. This embodiment is proposed based on this situation. In step S140, the image data of each play area and the image data of the second image frame are compared for the second time to obtain a second comparison result. Step S150 is to determine the image data of the play area finally used in step S130 according to the second comparison result.

[0078] There are many implementation methods of step S140 and step S150, and those skilled in the art can select a suitable method according to actual conditions, for example, subtract each playback area picture from the second image frame to obtain a difference image, and by counting the average difference of each difference image, it is considered that the playback area picture with the smallest average difference of the difference image is the actual playback area picture, and the playback area picture with the smallest average difference is used as the final playback area picture used in step S130. Of course, before comparison, each playback area picture and the second image frame can also be resampled to the same size to facilitate comparison.

[0079] In this implementation manner, during the processing of step S120, when more than one playback area is obtained, the actual playback area is found through a simple and quick method.

[0080] In one implementation, the process of processing the first image frame to obtain the playback area of ​​the display device in the first image frame includes: step S121 and step S122.

[0081] Step S121, processing the first image frame to obtain a display device area within the first image frame;

[0082] Step S122, extracting the playback area of ​​the display device in the display device area picture.

[0083] In practice, the display device has a border, so the area of ​​the display device obtained after processing the first image frame generally has a border. In this embodiment, the border is removed to extract the real playback area image.

[0084] There are many methods for removing the border and extracting the playback area image, such as separating the border and the playback area based on the color of the border, or obtaining the playback area image by comparing with a second image frame without a display device border.

[0085] In one embodiment, the method for acquiring the non-shielded area for target detection further includes: step S160 and step S170.

[0086] Step S160, processing the first image frame to obtain a second non-shielded area in the first image frame; wherein the second non-shielded area is an area outside the playback area of ​​the display device in the first image frame;

[0087] Step S170: obtaining a non-shielded area of ​​the first image frame based on the first non-shielded area and the second non-shielded area.

[0088] This embodiment is a method for obtaining a non-shielded area of ​​the entire first video.

[0089] In one implementation, the method for acquiring the non-shielded area for target detection further includes: step S101 and step S102.

[0090] Step S101, obtaining a time difference between a second video played by a display device in a first video and a second video obtained from an input source of the display device;

[0091] Step S102: acquiring the first image frame and the second image frame according to the time difference.

[0092] As mentioned above, the video in the display device captured by the camera has a time delay relative to the acquired second video, and this time delay (i.e., time difference) can be calculated by experiment. In this embodiment, this time difference is obtained, and the first image frame and the second image frame are captured according to this time difference.

[0093] Embodiment 2

[0094] Corresponding to the method of embodiment 1, as Figure 5 As shown, the present invention further provides a device 5 for acquiring a non-shielded area for target detection, comprising: an acquisition module 501 , a processing module 502 and an execution module 503 .

[0095] An acquisition module 501 is used to acquire a first image frame of a first video captured by a camera, and acquire a second image frame of a second video input from a display device, wherein the content captured by the camera includes a display device, and the display device is playing the second image frame;

[0096] A processing module 502 is used to process the first image frame to obtain a playback area of ​​a display device in the first image frame;

[0097] The analysis module 503 is used to perform a first comparison between the image data of the playback area and the image data of the second image frame and obtain a first comparison result, and obtain a first non-shielded area in the display device area in the first image frame based on the first comparison result.

[0098] In one implementation, the process of obtaining the first non-shielded area in the display device area in the first image frame based on the first comparison result includes the steps of:

[0099] Obtaining a first comparison result;

[0100] Obtaining a preliminary non-shielded area according to the first comparison result;

[0101] Obtaining a first minimum circumscribed rectangle based on the preliminary non-shielded area;

[0102] The area of ​​the first minimum circumscribed rectangle is used as the first non-shielding area.

[0103] In one implementation, the process of obtaining the first non-shielded area within the display device area in the first image frame based on the first comparison result further includes the steps of:

[0104] Obtaining a first comparison result;

[0105] Obtaining a preliminary non-shielded area according to the first comparison result;

[0106] Obtaining a first minimum circumscribed rectangle based on the preliminary non-shielded area;

[0107] Extending the bottom edge of the first minimum circumscribed rectangle to the bottom edge of the playback area to obtain a second minimum circumscribed rectangle;

[0108] The area of ​​the second minimum circumscribed rectangle is used as the first non-shielding area.

[0109] In one embodiment, the device for acquiring the non-shielded area of ​​the target detection also includes a screening module, which is used to perform a second comparison on the image data of all playback areas and the image data of the second image frame and obtain a second comparison result when more than one playback area is obtained, and determine the image data of the playback area used in the first comparison based on the second comparison result.

[0110] In one implementation, the process of processing the first image frame to obtain the playback area of ​​the display device in the first image frame includes the steps of:

[0111] Processing the first image frame to obtain a display device area within the first image frame;

[0112] A playback area of ​​the display device is extracted from the display device area.

[0113] In one embodiment, the processing module is further used to process the first image frame to obtain a second non-shielded area in the first image frame; wherein the second non-shielded area is an area outside a playback area of ​​a display device in the first image frame;

[0114] The analysis module is further configured to obtain a non-shielded area of ​​the first image frame based on the first non-shielded area and the second non-shielded area.

[0115] In one embodiment, the device for acquiring the non-shielded area of ​​the target detection also includes a time determination module, which is used to acquire the time difference between the second video played by the display device in the first video and the second video acquired from the input source of the display device; and acquire the first image frame and the second image frame according to the time difference.

[0116] In this device, for the scenario where target detection is performed when a teacher or lecturer is explaining content in front of the screen, the video in the display device input source is obtained and compared with the display device playback area in the video shot with the display device, so as to separate the background playback picture and the foreground non-shielded area where target detection is required, thereby solving the technical problems of large interference and inaccurate detection in the prior art, so that the teacher or lecturer can also perform target detection with high precision when explaining content in front of the screen.

[0117] Embodiment 3

[0118] An embodiment of the present invention further provides a storage medium on which computer instructions are stored. When the instructions are executed by a processor, the method for acquiring a non-shielded area for target detection of any of the above embodiments is implemented.

[0119] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, random access memories (RAM), read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0120] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the relevant technology. The computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, RAM, ROM, magnetic disks or optical disks.

[0121] Corresponding to the above-mentioned computer storage medium, in one embodiment, a computer device is also provided, which includes a memory, an encoder, and a computer program stored in the memory and run on the encoder, wherein when the encoder executes the program, the acquisition of the non-shielded area of ​​the target detection as in any one of the above-mentioned embodiments is realized.

[0122] The above-mentioned computer device is aimed at the scenario where a teacher or lecturer performs target detection while explaining content in front of the screen. By obtaining the video in the input source of the display device, and comparing it with the display device playback area in the video shot with the display device, the background playback picture and the foreground non-shielded area requiring target detection are separated. This solves the technical problems of large interference and inaccurate detection in the prior art, so that the teacher or lecturer can perform target detection with high precision while explaining content in front of the screen.

[0123] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0124] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for acquiring a non-shielded area for target detection, characterized in that: Includes steps: Acquire a first image frame of a first video captured by a camera, and acquire a second image frame of a second video input from a display device, wherein the content captured by the camera includes a display device, and the display device is playing the second image frame; Processing the first image frame to obtain a playback area of ​​a display device within the first image frame; A first comparison is performed on the image data of the playback area and the image data of the second image frame to obtain a first comparison result, and based on the first comparison result, a first non-shielded area in the display device area in the first image frame is obtained.

2. The method for acquiring a non-shielded area for target detection according to claim 1, characterized in that: The process of obtaining the first non-shielded area within the display device area in the first image frame based on the first comparison result includes the steps of: Obtaining a first comparison result; Obtaining a preliminary non-shielded area according to the first comparison result; Obtaining a first minimum circumscribed rectangle based on the preliminary non-shielded area; The area of ​​the first minimum circumscribed rectangle is used as the first non-shielding area.

3. The method for acquiring a non-shielded area for target detection according to claim 1, characterized in that: The process of obtaining the first non-shielded area within the display device area in the first image frame based on the first comparison result includes the steps of: Obtaining a first comparison result; Obtaining a preliminary non-shielded area according to the first comparison result; Obtaining a first minimum circumscribed rectangle based on the preliminary non-shielded area; Extending the bottom edge of the first minimum circumscribed rectangle to the bottom edge of the playback area to obtain a second minimum circumscribed rectangle; The area of ​​the second minimum circumscribed rectangle is used as the first non-shielding area.

4. The method for acquiring a non-shielded area for target detection according to claim 1, characterized in that: Also includes the steps: When more than one playback area is obtained, performing a second comparison on the image data of all the playback areas and the image data of the second image frame to obtain a second comparison result; Based on the second comparison result, the image data of the playback area used in performing the first comparison is determined.

5. The method for acquiring a non-shielded area for target detection according to claim 1, characterized in that: The process of processing the first image frame to obtain the playback area of ​​the display device in the first image frame includes the steps of: Processing the first image frame to obtain a display device area within the first image frame; A playback area of ​​the display device is extracted from the display device area.

6. The method for acquiring a non-shielded area for target detection according to claim 1, characterized in that: Also includes the steps: Processing the first image frame to obtain a second non-shielded area in the first image frame, wherein the second non-shielded area is an area outside a playback area of ​​a display device in the first image frame; A non-shielding area of ​​a first image frame is obtained based on the first non-shielding area and the second non-shielding area.

7. The method for acquiring a non-shielded area for target detection according to claim 1, characterized in that: Also includes the steps: Obtaining a time difference between a second video played by a display device in the first video and a second video obtained from an input source of the display device; The first image frame and the second image frame are acquired according to the time difference.

8. A device for acquiring a non-shielded area for target detection, characterized in that: include: an acquisition module, configured to acquire a first image frame of a first video captured by a camera, and acquire a second image frame of a second video input from a display device, wherein the content captured by the camera includes a display device, and the display device is playing the second image frame; A processing module, used for processing the first image frame to obtain a playback area of ​​a display device within the first image frame; The analysis module is used to perform a first comparison between the image data of the playback area and the image data of the second image frame and obtain a first comparison result, and based on the first comparison result, obtain a first non-shielded area in the display device area in the first image frame.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images