Video processing method, apparatus, device, storage medium and computer program product

Abstract

The application relates to a video processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a first video frame collected in a first shooting mode; the first shooting mode is used for indicating shooting at a target frame rate after frame reduction; the target frame rate is determined based on environment information of a target scene; a target video frame to be supplemented is generated according to the first video frame and the target frame rate; and the first video frame is subjected to frame supplementing processing based on the target video frame to obtain a video frame after frame supplementing. The method can solve the problem of video frame rate reduction caused by the environment of the target scene, ensures the video picture effect, and improves the video frame rate.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a video processing method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] With the continuous development of image technology and monitoring equipment, today's monitoring equipment can generate clear color images even when used in low-light environments, such as at night or in dark environments, effectively improving the recognition of monitored targets in the monitoring screen.

[0003] Current surveillance equipment typically outputs color, high-brightness surveillance footage in low-light environments by reducing the number of video frames captured and increasing the exposure time of each frame. While this method can output color surveillance footage in low-light conditions, the frame rate of the color surveillance footage is significantly reduced, resulting in choppy video and making it unusable for platforms or clients that require a high video frame rate. Summary of the Invention

[0004] Therefore, it is necessary to provide a video processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the video image quality in low-light environments, in order to address the aforementioned technical problems.

[0005] Firstly, this application provides a video processing method. The method includes:

[0006] Acquire a first video frame captured in a first shooting mode; the first shooting mode is used to indicate shooting at a target frame rate after frame reduction; the target frame rate is determined based on environmental information of the target scene.

[0007] Based on the first video frame and the target frame rate, generate the target video frame to be supplemented;

[0008] Based on the target video frame, the first video frame is subjected to frame interpolation to obtain the interpolated video frame.

[0009] In one embodiment, generating the target video frame to be supplemented based on the first video frame and the target frame rate includes:

[0010] The target frame interpolation position is determined based on the position of the first video frame and the target frame rate;

[0011] Based on the first video frame, determine the target video frame to be supplemented at the target frame replacement position.

[0012] In one embodiment, determining the target video frame to be supplemented at the target frame supplementation position based on the first video frame includes:

[0013] The preceding video frame corresponding to the target frame-filling position is copied to obtain the copied preceding video frame; the preceding video frame represents the first video frame located in the frame preceding the target frame-filling position.

[0014] The copied previous video frame is set as the target video frame to be supplemented at the target frame position.

[0015] In one embodiment, determining the target interpolation frame position based on the position of the first video frame and the target frame rate includes:

[0016] The time periods corresponding to multiple first video frames are averaged to obtain multiple supplementary frame positions;

[0017] If each of the first video frames falls into one of the plurality of interpolation positions, then the remaining interpolation positions other than the interpolation positions corresponding to each of the first video frames are determined as the target interpolation positions.

[0018] If the position of the first video frame is located between two adjacent supplementary frame positions, and the distance between the position of the first video frame and the closer supplementary frame position is less than a distance threshold, then the closer supplementary frame position is deleted, and the target supplementary frame position is obtained based on the remaining supplementary frame positions after deletion.

[0019] In one embodiment, before acquiring the first video captured in the first shooting mode, the method further includes:

[0020] If the ambient illumination information of the target scene is detected to meet the first environmental condition, the currently executed shooting mode will be switched to the first shooting mode.

[0021] In one embodiment, acquiring the first video frame captured in the first shooting mode includes:

[0022] Obtain the first image parameters corresponding to the first shooting mode; the first image parameters represent image adjustment parameters used to generate a color image when the ambient illumination information meets the first environmental conditions.

[0023] Obtain the first video frame captured according to the first image parameters.

[0024] In one embodiment, after obtaining the interpolated video, the method further includes:

[0025] If the ambient illumination information is detected to meet the second environmental condition, the first shooting mode will be switched to the second shooting mode; the second shooting mode is used to indicate that a preset frame rate is used for shooting processing; the second image parameter corresponding to the second shooting mode represents the image adjustment parameters for daytime imaging;

[0026] Acquire the second video frame captured in the second shooting mode.

[0027] Secondly, this application also provides a video processing apparatus. The apparatus includes:

[0028] The frame-down shooting module is used to acquire the first video frame captured in the first shooting mode; the first shooting mode is used to indicate that shooting should be performed at the target frame rate after frame downgrading; the target frame rate is determined based on the environmental information of the target scene;

[0029] The frame interpolation generation module is used to generate a target video frame to be interpolated based on the first video frame and the target frame rate.

[0030] The video interpolation module is used to perform interpolation processing on the first video frame based on the target video frame to obtain the interpolated video frame.

[0031] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0032] Acquire a first video frame captured in a first shooting mode; the first shooting mode is used to indicate shooting at a target frame rate after frame reduction; the target frame rate is determined based on environmental information of the target scene.

[0033] Based on the first video frame and the target frame rate, generate the target video frame to be supplemented;

[0034] Based on the target video frame, the first video frame is subjected to frame interpolation to obtain the interpolated video frame.

[0035] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0036] Acquire a first video frame captured in a first shooting mode; the first shooting mode is used to indicate shooting at a target frame rate after frame reduction; the target frame rate is determined based on environmental information of the target scene.

[0037] Based on the first video frame and the target frame rate, generate the target video frame to be supplemented;

[0038] Based on the target video frame, the first video frame is subjected to frame interpolation to obtain the interpolated video frame.

[0039] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0040] Acquire a first video frame captured in a first shooting mode; the first shooting mode is used to indicate shooting at a target frame rate after frame reduction; the target frame rate is determined based on environmental information of the target scene.

[0041] Based on the first video frame and the target frame rate, generate the target video frame to be supplemented;

[0042] Based on the target video frame, the first video frame is subjected to frame interpolation to obtain the interpolated video frame.

[0043] The aforementioned video processing method, apparatus, computer equipment, storage medium, and computer program product acquire a first video frame captured in a first shooting mode. The first shooting mode is used to indicate shooting at a target frame rate after frame reduction. The target frame rate is determined based on environmental information of the target scene. A target video frame to be supplemented is generated based on the first video frame and the target frame rate. Based on the target video frame, the first video frame is subjected to frame supplementation processing to obtain a frame-supplemented video frame. This method, by acquiring the target video frame using the target frame rate and then using the target video frame to supplement the first video frame, quickly and effectively improves the frame rate of the video image, solving the problem of video frame rate reduction caused by the environment of the target scene. While ensuring the video image quality, it also improves the video frame rate. Attached Figure Description

[0044] Figure 1 This is an application environment diagram of a video processing method in one embodiment;

[0045] Figure 2 This is a flowchart illustrating a video processing method in one embodiment;

[0046] Figure 3 This is a schematic diagram illustrating the determination of the target video frame to be supplemented at the target frame supplementation position in one embodiment;

[0047] Figure 4 This is a flowchart illustrating the steps of determining the target interpolation frame position based on the position of the first video frame and the target frame rate in one embodiment.

[0048] Figure 5 This is a schematic diagram illustrating the averaging of time periods corresponding to multiple first video frames in one embodiment;

[0049] Figure 6 This is a schematic diagram illustrating the intervals between multiple first video frames actually captured in one embodiment;

[0050] Figure 7 This is a schematic diagram of the position of the padded frame to be deleted in one embodiment;

[0051] Figure 8 This is a flowchart illustrating a video processing method in another embodiment;

[0052] Figure 9 This is a flowchart illustrating the video processing method in yet another embodiment;

[0053] Figure 10 This is a structural block diagram of a video processing device in one embodiment;

[0054] Figure 11 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0057] The video processing method provided in this application embodiment can be applied to, for example, Figure 1 The application environment shown is a smart home system, which may include: a router, a gateway, a terminal 101 (such as a mobile phone, tablet, or laptop), a server 102, and a camera 103 (such as a camera or a black light full-color camera). In the smart home system, the camera 103 can connect to the gateway via ZIGBEE / Bluetooth / WiFi, and the gateway and terminal can connect to the router via WiFi. Additionally, the terminal can also establish a network connection with the server via 2G / 3G / 4G / 5G, WiFi, etc., thereby obtaining data sent by the server.

[0058] Terminal 101 is used to provide local services to users. Server 102 can be implemented using a standalone server, a server cluster consisting of multiple servers, or a cloud server. In practical applications, after obtaining the interpolated video frames, the shooting device 103 can send the interpolated video frames to terminal 101 and / or server 102 for display and processing.

[0059] In one embodiment, the shooting device 103 acquires a first video frame captured in a first shooting mode; the first shooting mode is used to indicate that shooting is performed at a target frame rate after frame downsampling; the target frame rate is determined based on the environmental information of the target scene; the shooting device 103 generates a target video frame to be supplemented based on the first video frame and the target frame rate; the shooting device 103 performs frame supplementation processing on the first video frame based on the target video frame to obtain a supplemented video frame.

[0060] In another embodiment, the shooting device 103 sends the first video frame it captures in the first shooting mode to the terminal 101 and / or the server 102; then the terminal 101 and / or the server 102 obtain the first video frame captured in the first shooting mode; the first shooting mode is used to indicate shooting at a target frame rate after frame downsampling; the target frame rate is determined based on the environmental information of the target scene; the terminal 101 and / or the server 102 generate a target video frame to be supplemented according to the first video frame and the target frame rate; the terminal 101 and / or the server 102 perform frame supplementation processing on the first video frame based on the target video frame to obtain a frame supplemented video frame.

[0061] In one embodiment, such as Figure 2 As shown, a video processing method is provided. Taking the application of this method to an electronic device as an example, the electronic device can specifically be... Figure 1 The shooting device 103 can also be a server 102, a terminal 101, or it can be implemented through interaction between the shooting device 103 and at least one of the server 102 and the terminal 101. The method includes the following steps:

[0062] Step S201: Acquire the first video frame captured in the first shooting mode; the first shooting mode is used to indicate that the target frame rate after frame reduction is used for shooting; the target frame rate is determined based on the environmental information of the target scene.

[0063] Shooting modes refer to the different settings and functions used by a shooting device (such as a camera, webcam, or mobile phone) during shooting to adapt to different shooting needs and environments. In shooting mode, the device automatically sets corresponding shooting parameters, such as shutter speed (S), ISO, exposure compensation (EV), focus mode (AF), and white balance (WB). Shooting modes can be factory defaults to the device, and some devices also support user-defined personalized shooting modes. Different shooting modes are suitable for different scenarios and provide different shooting effects. Common shooting modes include Normal mode, Portrait mode, Creative Auto mode, HDR (High Dynamic Range) mode, and Professional mode.

[0064] The first shooting mode in this embodiment can be a shooting mode adapted to low-light conditions in the target scene. The first shooting mode may include requirements on the imaging frame rate of the shooting device (such as the target frame rate).

[0065] A video frame, also called a frame, is the smallest unit of a single image in video animation, equivalent to each shot on a film reel. A frame is a still image, and displaying frames quickly and continuously creates the illusion of motion. Therefore, a high frame rate can produce smoother and more realistic video content.

[0066] Video is composed of a series of continuous video frames played at a certain speed. Each still image in the video is called a video frame. In applications such as smart homes and intelligent transportation, each video frame in the surveillance video contains information such as the position, size, and color of all elements in the picture. Users can understand the situation of the application scenario by observing the video frames of the surveillance video.

[0067] In this embodiment, the first video frame refers to the video frame captured by the shooting device according to the image parameters indicated by the first shooting mode.

[0068] Frame rate is a unit of measurement for the number of frames displayed in a video per unit of time, that is, the number of frames refreshed per second. A higher frame rate (such as 60 FPS) can provide a smoother video playback experience, while a lower frame rate (such as 30 FPS) may result in a video that does not look smooth.

[0069] In this embodiment, the target frame rate after frame reduction refers to the frame rate set due to the influence of environmental information of the target scene. The target frame rate in the first shooting mode is lower than the frame rate in the normal shooting mode, or lower than the standard frame rate specified by the platform (such as a smart home platform) that interfaces with the shooting device. For example, when the target scene is dark, if the shooting device does not have supplementary lighting hardware such as infrared lights, the frame rate of the shooting device in the normal shooting mode cannot obtain a high-brightness color image. In this case, the shooting device can continue to capture video by applying a reduced target frame rate for the dark scene, so as to obtain the cumulative effect of image brightness by increasing the exposure time of a single video frame, so that the shooting device can output a bright image even in extremely dark environments. The target frame rate after frame reduction can be preset.

[0070] Here, the target scene refers to the spatial scene captured by the camera. Environmental information refers to parameters describing the environmental conditions of the target scene; for example, environmental information could be the current ambient illuminance of the target scene (unit: lux).

[0071] Specifically, the correlation between the environmental information of the target scene and the target frame rate can be preset. When the shooting device executes the first shooting mode, it can first collect the current environmental information of the target scene through the sensors equipped on the shooting device, and then shoot the target scene according to the target frame rate corresponding to the current environmental information, so that the shooting device obtains the first video frame of the target frame rate.

[0072] Taking environmental information as environmental illuminance as an example, the correlation between the current environmental illuminance of the target scene and the target frame rate of the shooting device is shown in Table 1.

[0073] Table 1

[0074]

[0075] Step S202: Generate the target video frame to be supplemented based on the first video frame and the target frame rate.

[0076] The target video frame to be supplemented refers to the video frame that needs to be inserted between the first video frame. The shooting device captures the first video frame at the target frame rate after frame downsampling, resulting in a low frame rate for the corresponding video frame. During video processing, inserting the target video frame between the first video frames can increase the frame rate of the video captured by the shooting device in the first shooting mode. The target video frame is a video frame obtained by processing the first video frame. In practical applications, the target video frame can be obtained by copying the first video frame; that is, the target video frame can be identical to the first video frame.

[0077] It should be noted that, in order to meet the shooting effect of the shooting equipment in specific environments (such as nighttime environments), the number of video frames captured per unit time is usually reduced, and the exposure time of a single video frame is increased to improve the picture quality of a single video frame (such as increasing the brightness of a single video frame). Therefore, the target frame rate is lower than the standard frame rate specified by the platform that interfaces with the shooting equipment (such as a smart home platform).

[0078] Specifically, in order to meet the standard frame rate requirements of the platform that interfaces with the shooting equipment, the shooting equipment needs to determine the number of frames to be supplemented based on the target frame rate and the standard frame rate; then, based on the first video frame, it generates the target video frames that need to be supplemented.

[0079] Step S203: Based on the target video frame, perform frame interpolation on the first video frame to obtain the interpolated video frame.

[0080] Frame interpolation refers to the process of interpolating video frames to increase the number of frames, improve frame rate, or enhance video playback smoothness. When processing video frames, frame interpolation can help resolve issues such as insufficient frame rate, stuttering during video playback, and failure to meet the frame rate requirements of compatible platforms.

[0081] In this context, a padded video frame refers to a video frame obtained after frame padded processing. During video processing, electronic devices can insert one or more video frames into the original video frame to obtain a higher frame rate. Compared to the first video frame, the padded video frame has a higher frame rate, resulting in smoother video playback and meeting the frame rate requirements of the interfacing platform. A padded video frame can include both the first video frame and the target video frame.

[0082] Specifically, the shooting device supplements the generated target video frame between multiple first video frames to form a frame-supplemented video frame; it can also save the frame-supplemented video frame and send it to the target platform for playback.

[0083] In the aforementioned video processing method, a first video frame captured in a first shooting mode is acquired; the first shooting mode is used to indicate shooting at a target frame rate after frame reduction; the target frame rate is determined based on environmental information of the target scene; a target video frame to be supplemented is generated based on the first video frame and the target frame rate; and frame supplementation processing is performed on the first video frame based on the target video frame to obtain the supplemented video frame. This method, by acquiring the target video frame using the target frame rate and then using the target video frame to supplement the first video frame, quickly and effectively improves the video frame rate, solving the problem of video frame rate reduction caused by the environment of the target scene. While ensuring the video image quality, it also improves the video frame rate.

[0084] In one embodiment, step S202 above, generating a target video frame to be supplemented based on the first video frame and the target frame rate, specifically includes the following: determining the target supplementation frame position based on the position of the first video frame and the target frame rate; and determining the target video frame to be supplemented based on the target supplementation frame position of the first video frame.

[0085] The target frame interpolation position is used to characterize the position in the video captured by the shooting device in the first shooting mode where video frames need to be supplemented.

[0086] Specifically, the shooting device calculates the positions in the video that need to be interpolated based on the position of the first video frame and the number of frames that need to be interpolated, thus determining the target interpolation positions. For example, suppose the shooting device currently captures 5 first video frames, but the platform it is connected to requires a frame rate of 20 frames per second. In this case, 15 target video frames need to be inserted between the original 5 captured first video frames. That is, 15 target interpolation positions need to be determined between these 5 first video frames. These target interpolation positions can be evenly distributed or calculated using an algorithm.

[0087] The capturing device then uses the first video frame near the target frame-filling position as a basis to generate a target video frame to be filled in at the target frame-filling position. For example, it can synthesize a new video frame for the target frame-filling position based on the first video frame near the target frame-filling position; or it can copy a video frame that is exactly the same as the first video frame as the target video frame for the target frame-filling position.

[0088] In this embodiment, the target interpolation position in the first video frame captured in the first shooting mode is first determined. Then, based on the first video frame adjacent to the target interpolation position, a target video frame corresponding to each target interpolation position is generated. This allows subsequent steps to use the target video frame to perform interpolation processing on the first video frame, thereby improving the frame rate of the video captured in the first shooting mode. Moreover, generating the target video frame based on the first video frame adjacent to the target interpolation position can also reduce the impact of the interpolated video frame on the overall smoothness of the video picture during playback, thus improving the playback effect of the interpolated video frame.

[0089] In one embodiment, the above steps, based on the first video frame, determine the target video frame to be supplemented at the target supplementation position, specifically including the following: copying the previous video frame corresponding to the target supplementation position to obtain the copied previous video frame; the previous video frame represents the first video frame located in the frame before the target supplementation position; and setting the copied previous video frame as the target video frame to be supplemented at the target supplementation position.

[0090] The preceding video frame refers to the first video frame located before the target interpolation position. It should be noted that the preceding video frame must be the first video frame captured by the shooting device in the first shooting mode, and not a video frame filled in through interpolation.

[0091] Here, the copied previous video frame refers to the video frame obtained by copying the previous video frame. Since the copied previous video frame is obtained by copying the previous video frame, the copied previous video frame has the same content as its corresponding previous video frame.

[0092] Specifically, the shooting device determines the first video frame preceding the target interpolation position based on the position of each first video frame, and sets it as the preceding video frame corresponding to that target interpolation position. This preceding video frame is then copied to obtain a copied preceding video frame, which is set as the target video frame to be interpolated at the target interpolation position. For example, suppose there are originally 5 first video frames: frame 1, frame 2, frame 3, frame 4, and frame 5. If the target interpolation position is located between frame 3 and frame 4, then the preceding video frame corresponding to that target interpolation position is frame 3. You can then automatically copy one of the first video frames (frame 3), or copy one of the first video frames (frame 3) using the copy command or a manual shortcut (such as Ctrl+C). This copied first video frame (frame 3) will be the previous video frame after the copy. Then, you can paste the copied first video frame (frame 3) into the target frame position using the paste command or a manual shortcut (such as Ctrl+V).

[0093] It should be noted that if multiple target frame replacement positions correspond to the same first video frame, then the target video frames to be replaced at these multiple target replacement positions can be the same copied previous video frame. Figure 3 A diagram illustrating the target video frame to be supplemented to determine the target frame position, as shown below. Figure 3 As shown, the target video frames corresponding to the five target frame interpolation positions between the first video frame 1 and the first video frame 2 are all the first video frame 1; the target video frames corresponding to the five target frame interpolation positions between the first video frame 2 and the first video frame 3 are all the first video frame 2; the target video frame corresponding to the one target frame interpolation position between the first video frame 3 and the first video frame 4 is the first video frame 3; and the target video frames corresponding to the four target frame interpolation positions between the first video frame 4 and the first video frame 5 are the first video frame 4.

[0094] In this embodiment, the previous video frame corresponding to the target frame-filling position is copied as the target video frame to be filled in. This allows the target video frame to be filled in to keep the screen still during playback, with the same playback effect as the first video frame before frame-filling. Therefore, the overall smoothness of the screen during playback is not changed, effectively ensuring the playback effect of the video frame after frame-filling.

[0095] In one embodiment, such as Figure 4 As shown, the above steps determine the target interpolation frame position based on the position of the first video frame and the target frame rate, specifically including the following:

[0096] Step S401: Average the time periods corresponding to multiple first video frames to obtain multiple supplementary frame positions.

[0097] The time period is used to describe the continuous time interval between one point in time and another. In this embodiment, the time period refers to the start and end times of multiple first video frames. For example, if the total start and end times of multiple first video frames are from 16:00:00 to 16:00:01, then this start and end time is the time period corresponding to these first video frames. The time period also indicates that the multiple first video frames were acquired successively within this time period.

[0098] Averaging refers to dividing a time period into equal parts according to a certain number (such as the number of frames on the platform). For example, if the time period corresponding to multiple first video frames is 1 second in total, and the platform requires 20 frames, then averaging can be used to divide this 1 second into 20 sub-time periods.

[0099] The frame replacement position refers to the initially planned location where additional video frames need to be added.

[0100] Specifically, the shooting device calculates the sum of time periods corresponding to multiple first video frames. For example, it can calculate the sum of time periods corresponding to multiple first video frames by multiplying the time of each first video frame by the number of first video frames. Then, the sum of time periods is averaged. For example, it can be divided into the corresponding number of frames according to the frame rate requirements of the platform being connected, and multiple sub-time periods with uniform time intervals are calculated. Then, the position of the supplementary frame is obtained based on the time information corresponding to each sub-time period.

[0101] Figure 5This diagram illustrates the averaging of time periods corresponding to multiple first video frames. Taking a standard frame rate of 20 frames per second as an example, if the time period corresponding to multiple first video frames is 1 second, and the shooting device divides 1 second into 20 equal parts, then the time interval between two adjacent frame interpolation positions is 1 / 20 second. That is to say, the frame interpolation positions can be 0.05 seconds, 0.1 seconds, 0.15 seconds, ..., 0.95 seconds.

[0102] Step S402: If each first video frame falls into multiple interpolation positions, then the remaining interpolation positions other than the interpolation positions corresponding to each first video frame are determined as the target interpolation positions.

[0103] In this context, the first video frame falling into one of multiple interpolation frame positions means that the position of the first video frame is the same as the position of an interpolation frame, or the distance between the position of the first video frame and the interpolation frame position is within a preset range (i.e., the position of the first video frame and the interpolation frame position are "close"). For example, if the position of a first video frame is 0.05 seconds, and it happens to be the same as an interpolation frame position (0.05 seconds), then the first video frame can be considered to have fallen into this interpolation frame position. As another example, if the position of a first video frame is 0.05 seconds, and the distance between it and an interpolation frame position (0.049 seconds) is within a preset range (within 0.001 seconds), it means that the position of the first video frame is very close to this interpolation frame position, and thus the first video frame can also be considered to have fallen into this interpolation frame position.

[0104] Specifically, if the position of each first video frame is the same as the position of the supplementary frame, it means that the first video frame already exists at the supplementary frame position and no supplementary frame processing is required; if the distance between the position of each first video frame and the supplementary frame position is similar, for example, the distance between the position of the first video frame and the supplementary frame position is within a preset distance range, it means that no supplementary frame processing is required at the supplementary frame position; then the shooting device can set the remaining supplementary frame positions obtained in the above step S301, excluding the supplementary frame positions that are the same as or similar to each first video frame, as the target supplementary frame position.

[0105] Step S403: If the position of the first video frame is located between two adjacent supplementary frame positions, and the distance between the position of the first video frame and the closer supplementary frame position is less than the distance threshold, then the closer supplementary frame position is deleted, and the target supplementary frame position is obtained based on the remaining supplementary frame positions after deletion.

[0106] From the perspective of the video timeline, the position of the first video frame and the position of the interpolated frames refer to their positions on the timeline. The position of the first video frame is located between two adjacent interpolated frame positions, indicating that the time point corresponding to the position of the first video frame is between the time points corresponding to the two adjacent interpolated frame positions. For example, the time point corresponding to the position of the first video frame may be between 0.05 seconds and 0.1 seconds.

[0107] Specifically, if one or more first video frames are located between two adjacent supplementary frame positions, the system further determines whether the distance between the first video frame and its nearest supplementary frame position is less than a preset distance threshold. If it is less, the nearest supplementary frame position is deleted; otherwise, it is not deleted. After deleting the supplementary frame positions to which each first video frame falls, and deleting the supplementary frame positions closer to the first video frame when its position is between two adjacent supplementary frame positions, the shooting device uses the remaining supplementary frame positions as target supplementary frame positions.

[0108] In practical applications, due to fluctuations in ambient illumination, the intervals between frames in the multiple first video frames captured by the shooting device at the target frame rate after frame reduction are not uniform. Taking the current ambient illumination of the target scene as 0.11 lux as an example, the intervals between the multiple first video frames actually captured by the shooting device are as follows: Figure 6 As shown. The actual position of the first video frame may also fall exactly as shown. Figure 5 The evenly distributed interpolation positions shown may also fall between other evenly distributed interpolation positions. Interpolation positions that are the same as the first video frame, and interpolation positions whose distance from the first video frame is within a preset distance range, are deleted. For interpolation positions that fall between the evenly distributed interpolation positions, interpolation positions that are closer to the first video frame are deleted. Figure 7 This is a diagram showing the positions of the frames that need to be deleted.

[0109] In this embodiment, by averaging the time periods corresponding to multiple first video frames, multiple interpolation positions that need to be interpolated are initially determined. Then, based on the distance between the position of the first video frame and the multiple interpolation positions, interpolation positions that are the same as or close to the position of the first video frame are deleted. Finally, the remaining interpolation positions after deletion are set as the target interpolation positions. This achieves a reasonable determination of the target interpolation position to be interpolated, which meets the standard frame rate requirements of the target platform and does not affect the overall smoothness of the video after interpolation.

[0110] In one embodiment, before obtaining the first video frame captured in the first shooting mode in step S201 above, the method further includes: if the ambient illumination information of the target scene is detected to meet the first environmental condition, then the currently executed shooting mode is switched to the first shooting mode.

[0111] The target scene refers to a specific area or scene captured by the camera. For example, a target scene can be an indoor area such as a living room, bedroom, or balcony, or an outdoor area such as a garden, sports field, or sidewalk. The target scene can be selected based on the needs of the specific application area. For instance, application areas such as security monitoring, smart living, traffic monitoring, and motion analysis each have their own focused scenes and monitoring targets.

[0112] Ambient illuminance information is a physical quantity used to characterize the light intensity of a target scene. It also measures the luminous flux received per unit area of ​​the target scene, typically measured in lux. Ambient illuminance information can be acquired through sensors, cameras, or other measuring devices; for example, a light sensor can detect ambient light in real time. The intensity of light in the target scene can affect the imaging angle of the camera. In low-light environments, it may be necessary to activate the camera's night vision function, supplemental lighting, or adjust the camera's settings. In practical applications, ambient illuminance is affected by various factors, including natural light (such as sunlight and daylight), artificial light sources (such as lamps), time (such as day-night cycles), and weather (such as cloudy or rainy weather).

[0113] Here, environmental conditions refer to the judgment conditions set for the environmental information of the target scene. Environmental conditions can include condition information set for various aspects of environmental information such as ambient illuminance, ambient illuminance range, and light source type. In this embodiment, the first environmental condition is used to analyze and determine whether the target scene is in a dimly lit environment (such as a nighttime environment or a dark environment); for example, the first environmental condition can be set to an ambient illuminance of less than 2 lux. If the current ambient illuminance is detected to be 0.11 lux, then the first environmental condition can be considered to be met.

[0114] Specifically, the shooting device can detect the ambient illuminance information of the target scene through its built-in light sensor. When the current ambient illuminance information of the target environment meets the first environmental condition, such as when the current ambient illuminance information of the target environment is lower than the preset illuminance threshold, the shooting device needs to switch the currently executed shooting mode (such as the second shooting mode) to the first shooting mode in order to reduce the frame rate and achieve brightness compensation of the video image. It should be noted that if the currently executed shooting mode is the first shooting mode, then there is no need to switch the shooting mode.

[0115] In this embodiment, if the light sensor built into the shooting device detects that the ambient illuminance information of the target scene meets the first environmental condition, the shooting device starts the first shooting mode to compensate for the brightness of the video image. By reducing the frame rate of the first video frame, the true color of the target scene in the first video frame is restored. There is no need to deploy additional lighting equipment for the shooting device, and the shooting effect of the shooting device under the first environmental condition (such as night or dark environment) is also improved.

[0116] In one embodiment, step S201, acquiring the first video frame captured in the first shooting mode, specifically includes the following: acquiring the first image parameters corresponding to the first shooting mode; the first image parameters characterize image adjustment parameters used to generate a color image when the ambient illumination information meets the first environmental conditions; and acquiring the first video frame captured according to the first image parameters.

[0117] Image parameters refer to metrics and parameters related to image quality. Image parameters describe various aspects of an image, such as sharpness, detail, and color accuracy. In this embodiment, the first image parameter can be an image adjustment parameter (IQ) adapted to black-light full-color imaging. For example, the first image parameter may include requirements for various parameters such as frame rate, contrast, color saturation, noise, sharpness, and format of video frames captured in the first shooting mode. In practical applications, the first image parameter can be set based on experience or through specific algorithms or platform requirements to optimize the quality and display effect of video frames captured in the first shooting mode.

[0118] The image adjustment parameters include various parameters such as noise, sharpness, and color reproduction of video frames. The first shooting mode is used to characterize the mode of restoring the colors of objects in darker environments by reducing the frame rate.

[0119] Specifically, when the ambient light of the target scene decreases to the point where the first shooting mode needs to be entered, the shooting device will load the first image parameters corresponding to the first shooting mode, such as loading the image adjustment parameter file for black light full-color imaging. This image adjustment parameter file can determine the target frame rate after frame reduction and restore the true color of objects in the target scene in the imaging based on the ambient light information, thereby capturing the first video frame of color imaging at the target frame rate.

[0120] In this embodiment, the first video frame is captured using the first image parameters corresponding to the first shooting mode, which realizes color reproduction of the video image in a low-light environment. There is no need to deploy additional lighting equipment for the shooting device, which saves equipment costs and improves the shooting effect of the shooting device in a low-light environment.

[0121] In one embodiment, after obtaining the interpolated video frame in step S203, the method further includes: if the ambient illumination information is detected to meet the second environmental condition, the first shooting mode is switched to the second shooting mode; the second shooting mode is used to indicate that a preset frame rate is used for shooting processing; the second image parameter corresponding to the second shooting mode represents the image adjustment parameter for daytime imaging; and the second video frame acquired in the second shooting mode is obtained.

[0122] The second environmental condition is used to analyze and determine whether the target scene is in a bright environment (such as a daytime environment). The second environmental condition can be set based on the ambient illuminance information or the ambient illuminance range of the target scene. For example, the second environmental condition can be set to an ambient illuminance range of [2 lux, 5 lux). If the current ambient illuminance information is detected to be 2.5 lux, then the second environmental condition can be considered to be met.

[0123] The second shooting mode is designed for shooting in brighter lighting conditions. It may also include requirements for the imaging frame rate of the shooting device (such as the target frame rate). Unlike the first shooting mode, which is primarily designed for brighter lighting conditions, the second shooting mode is designed for dimmer lighting conditions. Therefore, the frame rate requirement for the second shooting mode is higher than that for the first shooting mode.

[0124] The second image parameters can be image adjustment parameters adapted for daytime imaging. For example, the second image parameters can include requirements for various parameters such as frame rate, contrast, color saturation, noise, sharpness, and format of video frames captured in the second shooting mode. In practical applications, the second image parameters can also be set based on experience, or through specific algorithms or platform requirements, to optimize the quality and display effect of video frames captured in the second shooting mode. It is understandable that because the second shooting mode is for shooting in brighter environments, while the first shooting mode is for shooting in darker environments, the second image parameters are usually different from the first image parameters. For example, the frame rate requirement for the second image parameters is usually higher than that for the first image parameters.

[0125] Specifically, the shooting device can detect the ambient illuminance information of the target scene through its built-in light sensor. When the current ambient illuminance information of the target environment meets the second environmental condition, such as when the current ambient illuminance information of the target environment is higher than the preset illuminance threshold, the shooting device needs to switch the currently executed shooting mode (such as the first shooting mode) to the second shooting mode in order to improve the frame rate and enter the normal shooting state.

[0126] At this point, the shooting device will load the second image parameters corresponding to the second shooting mode, such as loading an image adjustment parameter file for daytime imaging. This daytime imaging image adjustment parameter file can capture video at the standard frame rate of the target platform connected to the shooting device, thereby allowing the shooting device to capture a second video frame at the standard frame rate. The second video frame refers to the video frame captured according to the image parameters indicated by the second shooting mode. Since the second image parameters of the second shooting mode conform to the standard frame rate specified by the platform connected to the shooting device, the frame rate of the second video frame captured through the second shooting mode conforms to the standard frame rate specified by the platform connected to the shooting device. However, the target frame rate of the first shooting mode is lower than the standard frame rate specified by the platform connected to the shooting device, so the frame rate of the first video frame captured through the first shooting mode is lower than the standard frame rate specified by the platform connected to the shooting device; that is, the frame rate of the second video frame is higher than the frame rate of the first video frame. Furthermore, since the ambient illumination during the day is better than at night, the brightness and color of the second video frame are usually also better than those of the first video frame.

[0127] In this embodiment, by detecting whether the ambient illuminance information meets the second environmental conditions, the flexible switching between the first shooting mode and the second shooting mode is realized. In turn, the second video frame can be captured according to the second image parameters corresponding to the second shooting mode, realizing video frame acquisition in a daytime environment with good lighting, and improving the flexibility of video processing of the shooting device.

[0128] In one embodiment, such as Figure 8 As shown, another video processing method is provided, which can be applied to... Figure 1 Taking the shooting equipment in the image as an example, the following steps are included:

[0129] Step S801: If the ambient illumination information of the target scene is detected to meet the first environmental condition, the currently executed shooting mode is switched to the first shooting mode.

[0130] Step S802: Obtain the first image parameters corresponding to the first shooting mode; the first image parameters represent the image adjustment parameters used to generate a color image when the ambient illumination information meets the first environmental conditions.

[0131] Step S803: Obtain the first video frame captured according to the first image parameters.

[0132] Step S804: Determine the target frame replacement position based on the position of the first video frame and the target frame rate.

[0133] Step S805: Based on the first video frame, determine the target video frame to be supplemented at the target frame position.

[0134] Step S806: Based on the target video frame, perform frame interpolation on the first video frame to obtain the interpolated video frame.

[0135] Step S807: If the ambient illumination information is detected to meet the second environmental condition, the first shooting mode will be switched to the second shooting mode; the second shooting mode is used to indicate that the shooting process is performed using a preset frame rate; the second image parameters corresponding to the second shooting mode represent the image adjustment parameters for daytime imaging.

[0136] Step S808: Acquire the second video frame captured in the second shooting mode.

[0137] The above video processing method can achieve the following beneficial effects: by using the target frame rate to obtain the target video frame, and then using the target video frame to perform frame interpolation processing on the first video frame, the frame rate of the video picture is quickly and effectively improved, solving the problem of video frame rate drop caused by the environment of the target scene. While ensuring the video picture quality, the frame rate of the video is also improved.

[0138] To more clearly illustrate the video processing method provided in this disclosure, a specific embodiment will be used to describe the video processing method below. For example... Figure 9 As shown, another video processing method is provided that can be applied to... Figure 1 The filming equipment used in the project includes the following:

[0139] (1) Start the shooting device (e.g., a camera) that is capable of black light full color imaging and whose normal frame rate in daytime working mode is 20 frames.

[0140] (2) After the shooting device is started, the ambient light level is detected by the built-in light sensor in the shooting device to see if the current ambient light level meets the conditions for starting the black light full color mode.

[0141] (3) If not satisfied, the shooting device loads the daytime image adjustment parameters and shoots at the standard frame rate required by the target platform that is connected to the shooting device.

[0142] (4) If satisfied, the shooting device loads the black light full-color image adjustment parameters and shoots at the target frame rate of frame reduction to achieve brightness compensation of the captured image through frame reduction. Among them, the black light full-color image adjustment parameters include parameters such as image noise, sharpness, and color reproduction.

[0143] (5) The shooting device can also determine specific imaging parameters (such as the frame rate after frame downgrading, the number of frames to be supplemented, color reproduction, etc.) based on the current illumination value of the shooting environment, thereby automatically supplementing the number of frames between the target frame rate and the standard frame rate.

[0144] For example, when the illuminance is 0.1 lux, the imaging frame rate of the camera will drop to 12 frames per second. Compared to the standard 20 frames per second for daytime imaging, 8 more frames need to be added. During the frame addition process, the unit time of the video can be divided into 20 equal parts. Then, based on the positions of the existing 12 video frames, the positions of the 8 additional video frames to be added are determined. At each addition position, the copied previous video frame is inserted, and finally, the video with added frames is obtained.

[0145] (6) The light sensor will continuously detect whether the current ambient light level meets the conditions for turning off the black light full color mode. For example, when the current ambient light level rises to the point where it is no longer necessary to compensate for the brightness of the image by reducing the frame rate, the shooting device will end the working state of reducing and supplementing the frame rate and enter the daytime working mode; at this time, the shooting device will automatically load the image adjustment parameters for daytime imaging, and the frame rate of the shooting device will also return to the normal 20 frames per second.

[0146] (7) Finally, the shooting equipment will be taken out of service, completing one work cycle.

[0147] In this embodiment, the problem of reduced frame rate of video frames acquired when capturing color imaging video frames due to decreased ambient light is solved. It also eliminates the need to deploy additional supplementary lighting equipment for the shooting device. While saving equipment costs, it also improves the frame rate of video frames captured by the shooting device in low ambient light conditions, thereby improving the smoothness of the image and the imaging effect of the shooting device in low ambient light conditions.

[0148] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0149] Based on the same inventive concept, this application also provides a video processing apparatus for implementing the video processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more video processing apparatus embodiments provided below can be found in the limitations of the video processing method described above, and will not be repeated here.

[0150] In one embodiment, such as Figure 10 As shown, a video processing device 1000 is provided, including: a frame-down capture module 1001, a frame-interpolation generation module 1002, and a video frame-interpolation module 1003, wherein:

[0151] The frame-down shooting module 1001 is used to acquire the first video frame captured in the first shooting mode; the first shooting mode is used to indicate that the target frame rate after frame downgrading is used for shooting; the target frame rate is determined based on the environmental information of the target scene.

[0152] The frame interpolation generation module 1002 is used to generate target video frames to be interpolated based on the first video frame and the target frame rate.

[0153] The video interpolation module 1003 is used to perform interpolation processing on the first video frame based on the target video frame to obtain the interpolated video frame.

[0154] In one embodiment, the frame interpolation generation module 1002 is further configured to determine the target interpolation frame position based on the position of the first video frame and the target frame rate; and to determine the target video frame to be interpolated based on the first video frame.

[0155] In one embodiment, the video processing apparatus 1000 further includes a frame interpolation determination module, which is used to copy the previous video frame corresponding to the target frame interpolation position to obtain a copied previous video frame; the previous video frame represents the first video frame located in the frame preceding the target frame interpolation position; and the copied previous video frame is set as the target video frame to be interpolated at the target frame interpolation position.

[0156] In one embodiment, the video processing device 1000 further includes a position determination module, which is used to average the time periods corresponding to the multiple first video frames to obtain multiple supplementary frame positions; if each first video frame falls into the multiple supplementary frame positions, the remaining supplementary frame positions other than the supplementary frame positions corresponding to each first video frame are determined as target supplementary frame positions; if the position of the first video frame is located between two adjacent supplementary frame positions, and the distance between the position of the first video frame and the closer supplementary frame position is less than a distance threshold, the closer supplementary frame position is deleted, and the target supplementary frame position is obtained based on the remaining supplementary frame positions after deletion.

[0157] In one embodiment, the video processing device 1000 further includes a first switching module, configured to switch the currently executed shooting mode to the first shooting mode if the ambient illumination information of the target scene is detected to meet the first environmental conditions.

[0158] In one embodiment, the frame-down shooting module 1001 is further configured to obtain first image parameters corresponding to the first shooting mode; the first image parameters represent image adjustment parameters used to generate a color image when the ambient illumination information meets the first environmental conditions; and obtain the first video frame captured according to the first image parameters.

[0159] In one embodiment, the video processing device 1000 further includes a second switching module, configured to switch the executed first shooting mode to a second shooting mode if the detected ambient illumination information meets the second environmental conditions; the second shooting mode is used to indicate that shooting processing is performed using a preset frame rate; the second image parameters corresponding to the second shooting mode characterize the image adjustment parameters for daytime imaging; and acquire the second video frame captured in the second shooting mode.

[0160] Each module in the aforementioned video processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0161] In one embodiment, a computer device is provided, which may be a camera device, and its internal structure diagram may be as follows: Figure 11 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data such as the first video frame and interpolated video frames. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a video processing method.

[0162] Those skilled in the art will understand that Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0163] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0164] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0165] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0166] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0167] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above 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.

[0168] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A video processing method, characterized in that, The method includes: Acquire a first video frame of color imaging captured in a first shooting mode; the first shooting mode is used to indicate shooting at a target frame rate after frame reduction; the target frame rate is determined based on environmental information of the target scene; the first shooting mode is used to characterize a mode that restores the color of objects in a dark environment by reducing the frame rate and loading image adjustment parameters that enable color imaging. Based on the first video frame and the target frame rate, generate the target video frame to be supplemented; Based on the target video frame, the first video frame is subjected to frame interpolation to obtain the interpolated video frame.

2. The method according to claim 1, characterized in that, The step of generating the target video frame to be supplemented based on the first video frame and the target frame rate includes: The target frame interpolation position is determined based on the position of the first video frame and the target frame rate; Based on the first video frame, determine the target video frame to be supplemented at the target frame replacement position.

3. The method according to claim 2, characterized in that, The step of determining the target video frame to be supplemented at the target frame position based on the first video frame includes: The preceding video frame corresponding to the target frame-filling position is copied to obtain the copied preceding video frame; the preceding video frame represents the first video frame located in the frame preceding the target frame-filling position. The copied previous video frame is set as the target video frame to be supplemented at the target frame position.

4. The method according to claim 2, characterized in that, Determining the target interpolation frame position based on the position of the first video frame and the target frame rate includes: The time periods corresponding to multiple first video frames are averaged to obtain multiple interpolation frame positions; If each of the first video frames falls into one of the plurality of interpolation positions, then the remaining interpolation positions other than the interpolation positions corresponding to each of the first video frames are determined as the target interpolation positions. If the position of the first video frame is located between two adjacent supplementary frame positions, and the distance between the position of the first video frame and the closer supplementary frame position is less than a distance threshold, then the closer supplementary frame position is deleted, and the target supplementary frame position is obtained based on the remaining supplementary frame positions after deletion.

5. The method according to claim 1, characterized in that, Before acquiring the first video of the color image captured in the first shooting mode, the process also includes: If the ambient illumination information of the target scene is detected to meet the first environmental condition, the currently executed shooting mode will be switched to the first shooting mode.

6. The method according to claim 5, characterized in that, The acquisition of the first video frame of the color image captured in the first shooting mode includes: Obtain the first image parameters corresponding to the first shooting mode; the first image parameters represent image adjustment parameters used to generate a color image when the ambient illumination information meets the first environmental conditions. Obtain the first video frame captured according to the first image parameters.

7. The method according to claim 5, characterized in that, After obtaining the video with the interpolated frames, the process also includes: If the ambient illumination information is detected to meet the second environmental condition, the first shooting mode will be switched to the second shooting mode; the second shooting mode is used to indicate that a preset frame rate is used for shooting processing; the second image parameter corresponding to the second shooting mode represents the image adjustment parameters for daytime imaging; Acquire the second video frame captured in the second shooting mode.

8. A video processing apparatus, characterized in that, The device includes: A frame-down shooting module is used to acquire the first video frame of color imaging captured in a first shooting mode; the first shooting mode is used to indicate shooting at a target frame rate after frame downgrading; the target frame rate is determined based on the environmental information of the target scene; the first shooting mode is used to characterize a mode that restores the color of objects in a dark environment by downgrading the frame and loading image adjustment parameters that enable color imaging. The frame interpolation generation module is used to generate a target video frame to be interpolated based on the first video frame and the target frame rate. The video interpolation module is used to perform interpolation processing on the first video frame based on the target video frame to obtain the interpolated video frame.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

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

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images