33 results about "Slow motion" patented technology

The invention relates to the technical field of image communication, in particular to a video slow-action frame insertion playback system based on a generative adversarial network, which comprises a video signal acquisition module, a signal processing module, a frame rate conversion module and a playback code output module. The acquisition module outputs an original video frame sequence through an annular buffer; the processing module separates the denoised detail components and the edge gradient features in parallel; the frame rate conversion module uses a geometric structure as a boundary locking condition to guide detail components to execute nonlinear motion compensation and intermediate frame reconstruction; and the playback module executes time base remapping and distributed coding transmission. According to the invention, through a depth generation architecture of structural constraint textures, in combination with space-time consistency verification and a nearest neighbor pixel backfilling mechanism and a virtual time base rate decoupling technology, real-time slow-action video redisk with high signal-to-noise ratio and no artifacts for a high-speed moving target is realized.

The invention relates to a method for generating an audio signal accompanying a slow-motion video signal, comprising: generating a first graphical representation of the input audio signal, dividing the first graphical representation into a set of grains, wherein each has a length and a temporal position, inserting the grains into a second graphical representation representing the output audio signal at a temporal position corresponding to the original temporal position of the grains, corrected by a factor dependent on the slow-motion speed, generating, by audio inpainting based on diffusion, the filling grains intended to fill the spaces between the grains of the second representation, inserting the filling grains into the spaces between the grains, converting the second representation by applying the inverse of the first step.

The invention discloses a live broadcast wonderful instant slow playing and playback method and device, electronic equipment and a product, and the method comprises the steps: receiving a live broadcast stream in real time, the live broadcast stream having a live broadcast linear time code; encoding the received live stream by using a first linear time code and caching the encoded live stream in a memory to generate a live cache pool, and encoding the received live stream by using a second linear time code and storing the encoded live stream to form a live recording file; in response to the wonderful instant slow playing or playback request, obtaining a playing mode and a target time code of a wonderful instant starting position; and according to a comparison result of the target time code and the first linear time code of the start frame of the live broadcast cache pool, selecting the live broadcast cache pool or the live broadcast recording file, and executing a corresponding playing operation according to the playing mode. According to the method and the device, dynamic seamless switching from live broadcast recording to the live broadcast cache pool can be realized, and video playing from the live broadcast cache pool is preferentially realized, so that the video playing fluency and interactivity are improved, the delay of real-time playback is reduced, and the watching experience is improved.

The invention relates to a method for generating an audio signal accompanying a slow-motion video signal, comprising: generating a first graphical representation of the input audio signal, dividing the first graphical representation into a set of grains, wherein each has a length and a temporal position, inserting the grains into a second graphical representation representing the output audio signal at a temporal position corresponding to the original temporal position of the grains, corrected by a factor dependent on the slow-motion speed, generating, by audio inpainting based on diffusion, the filling grains intended to fill the spaces between the grains of the second representation, inserting the filling grains into the spaces between the grains, converting the second representation by applying the inverse of the first step.

The invention provides a slow action generation method based on motion focus area analysis. The method comprises the following steps: determining a video of a slow action to be generated; detecting a motion focus area in the video, and grading the motion focus area; and for different grades of motion focus areas, different strategies are adopted to carry out motion modeling and differential interpolation processing, and a slow motion frame sequence is generated. According to the invention, through identification and grading processing of the motion focus area, high-precision calculation of the core motion object, simplified calculation of the secondary area and simplest processing of the static background, compared with a traditional scheme of uniform and dense calculation of the whole frame, the method has the advantages of high calculation complexity and lower calculation amount, and guarantees the visual effect of the core area.

This invention discloses a weakly supervised video temporal action localization method based on slow-motion enhancement, which consists of a slow-motion correlation mining module and a localization module. The slow-motion correlation mining module takes fused video features as input and outputs a slow-motion correlation mask. The localization module takes the slow-motion correlation mask output by the slow-motion correlation mining module as input and generates slow-motion enhancement features. Then, using the slow-motion enhancement features and fused video features as input, a two-stream branch localization network is used to finally generate the temporal action localization result.

The application discloses a motion sensing game method and device based on hand waving, equipment and a computer readable storage medium. The motion sensing game method based on hand waving comprises the following steps: after starting the motion sensing game, acceleration data in horizontal direction or vertical direction is obtained from a bound motion sensing device; the motion path of a game object in the motion sensing game is determined according to the acceleration data; the displacement instruction of the game object is generated according to the acceleration data and a preset slow motion function; and the game object is controlled to move along the motion path in a nonlinear mode according to the displacement instruction. The motion sensing game method based on hand waving can provide more real, smooth and flexible user experience, and has better playability and game performance.

The invention discloses a video processing method and device, electronic equipment and a computer readable storage medium. The video quality and the video effect of a slow action video can be achieved. The method comprises the following steps: under the condition that video acquisition is started, storing an original video stream of a first frame rate into a target storage space through a target transmission channel by an image sensor; after acquisition is completed, performing frame insertion processing on the original video data at a second frame rate, and determining intermediate video data; the second frame rate is greater than the first frame rate; encoding the intermediate video data at a target encoding frame rate, and determining a target video; the target coding frame rate is smaller than the second frame rate.

This application provides a video processing method and an electronic device. The shooting environment of the electronic device includes a first strobe source with a flash period of a first period. The method includes: launching a camera application; displaying a first preview interface; receiving a first instruction input by a user based on the first preview interface, the first instruction indicating that the shooting mode be set to a first mode, the target recording frame rate corresponding to the first mode being a first recording frame rate; and, in response to the first instruction, displaying a second preview interface if the reciprocal of the first recording frame rate is less than the first period, the second preview interface including first video data obtained based on a first exposure time and a second recording frame rate, wherein the first exposure time is equal to the first period, the second recording frame rate is less than the first recording frame rate, and the reciprocal of the second recording frame rate is greater than or equal to the first period. This method can improve the quality of slow-motion videos.

The application relates to the technical field of image communication, in particular to a video slow-motion frame insertion playback system based on a generative adversarial network, which comprises a video signal acquisition module, a signal processing module, a frame rate conversion module and a playback encoding output module. The acquisition module outputs an original video frame sequence through a ring buffer; the processing module parallelly separates a detail component after denoising and an edge gradient feature; the frame rate conversion module uses a geometric structure as a boundary locking condition, guides the detail component to execute nonlinear motion compensation and intermediate frame reconstruction; and the playback module executes time base remapping and distributed encoding transmission. Through a structure constraint texture depth generation architecture, in combination with a space-time consistency check and a nearest neighbor pixel backfilling mechanism and a virtual time base rate decoupling technology, the application realizes real-time slow-motion video review for high-speed moving targets with high signal-to-noise ratio and no artifacts.

1. The name of this design product: 360-degree panoramic camera. 2. Purpose of this product design: Used to shoot 360-degree surround slow-motion videos and photos. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: Stereoscopic drawing 1. 5. The bottom view has been shown in the stereoscopic view, so the bottom view is omitted.

The invention discloses a real-time high-multiple slow-action generation method and system for an ultra-high-definition video, and the method comprises the steps: cooperatively generating an intermediate frame through a dynamic scheduling strategy in combination with an optical flow algorithm and a frame mixing algorithm, caching an original video frame, and carrying out the real-time high-multiple slow-action generation according to a target slow-action multiple and a playing frame rate. The method comprises the following steps: dynamically determining the number and position of intermediate frames which need to be generated by an optical flow algorithm and a frame mixing algorithm, executing the optical flow algorithm by utilizing GPU parallel computing to generate high-quality intermediate frames, efficiently supplementing other intermediate frames by utilizing the frame mixing algorithm, and finally combining and outputting all the frames in sequence. Through an intelligent scheduling algorithm, on the premise that the picture fluency is guaranteed, the processing efficiency is remarkably improved, and high-multiple high-quality real-time slow action generation of the 4K / 8K ultra-high-definition video is achieved.

The invention relates to the technical field of VR, and provides a video transmission method, electronic equipment and virtual reality equipment. According to the method, pose data of a virtual reality device is added on the basis of a network bandwidth, when the pose data is received for the first time, a binocular image of a current frame image is coded according to a basic code rate determined by the network bandwidth, and when the pose data is not received for the first time, the binocular image of the current frame image is coded according to the pose variation of the pose data between adjacent frames. And calculating a target adjustment factor for adjusting the basic code rate to obtain a target code rate, and coding the binocular image of the current frame image by using the target code rate. Since the size of the target adjustment factor is positively correlated with the size of the pose variation, the adjusted code rate can adapt to the motion state of the head of the user, so that the code rate is improved during rapid motion to ensure the fluency of a display picture, and the code rate is reduced during static or slow motion to save bandwidth resources.

A compensating timer system and method utilizable with video data featuring sections of different playback or recording speeds. The compensating timer system can be utilized with a user interface associated with and displayable thereon. The user interface can include a video display region configured or configurable to display video data, and an animated time indicator. The animated time indicator can be dependent on a modified playing speed of the video data that changes between different first and second speed rates. The first speed rate can be changed to the second speed rate upon receipt of an input associated with an affordance, by modifying at least one frame in the video data. This allows for continuous recording and / or displaying of video at different speed rates without altering operations or settings. The animated time indicator can be an animated affordance, an animated progress bar, an elapsed timer and / or a time remaining clock.

The present application relates to the field of image processing, and discloses a video generation method, an electronic device, and a computer readable storage medium. The method comprises: turning on a first camera, and displaying a first interface, wherein a preview window of the first interface is used for displaying a preview stream picture. When an automatic snapshot mode in a camera function is enabled, an event camera is turned on to capture event camera stream information. If it is detected, on the basis of preview stream information corresponding to the preview stream picture, that a target object meets a preset motion attitude, N highlight frames for generating a video are determined on the basis of the preview stream information. The event camera stream information is acquired, and a first image to be inserted is determined on the basis of the information, wherein the first image comprises slow motion details of the target object in at least a pair of adjacent highlight frames among the N highlight frames; and a target highlight video is generated on the basis of the N highlight frames and the first image. Thus, the continuity and smoothness of video generation can be improved, and the user experience is improved.

This application relates to a video generation method, apparatus, computer device, and storage medium. The method includes: acquiring a first video stream captured by a main camera at a first frame rate, and a first event stream output by an event camera in a first acquisition mode; obtaining an event density based on the first event stream; if the event density meets a preset condition, controlling the event camera to switch to a second acquisition mode and acquiring a second event stream output by the event camera; and obtaining a second video stream based on the first video stream and the second event stream. This method enables low-power, long-duration, ultra-high frame rate slow-motion video generation.

The present invention discloses a method and device for video object segmentation using implicit motion compensation, which belongs to the field of video processing technology and is used to solve the technical problems of slow motion compensation network calculation, content redundancy, and low accuracy in unsupervised video object segmentation in existing video processing. The method comprises: extracting consecutive frames from a video to be processed, and extracting features from the consecutive frames using a shared feature encoder to obtain embedded features; calculating a similarity matrix on the embedded features to obtain a similarity matrix; normalizing the similarity matrix to obtain attention-enhanced features; skipping the embedded features of each layer to connect to a higher layer for prediction guidance to generate a final feature; aligning the final feature of the central frame with the final feature of each adjacent frame to obtain an aligned feature; fusing the aligned features to obtain a fused feature; performing segmentation prediction on the fused feature to obtain a predicted segmentation mask, so as to segment the video object using the predicted segmentation mask.

A compensating timer system and method utilizable with video data featuring sections of different playback or recording speeds. The compensating timer system can be utilized with a user interface associated with and displayable thereon. The user interface can include a video display region configured or configurable to display video data, and an animated time indicator. The animated time indicator can be dependent on a modified playing speed of the video data that changes between different first and second speed rates. The first speed rate can be changed to the second speed rate upon receipt of an input associated with an affordance, by modifying at least one frame in the video data. This allows for continuous recording and / or displaying of video at different speed rates without altering operations or settings. The animated time indicator can be an animated affordance, an animated progress bar, an elapsed timer and / or a time remaining clock.

The information processing device that outputs a plurality of slow-motion images to a display unit configured to simultaneously display the plurality of slow-motion images in a plurality of slow-motion display areas in parallel includes: a time range assigning unit configured to assign different time ranges to the slow-motion display areas; and a slow-motion data generating unit configured to generate slow-motion data which is a slow motion associated with a first parameter which is a parameter of time or corresponds to time with respect to reference data in which a second parameter varies with change of the first parameter for each of the slow-motion display areas on the basis of a result of assignment of the time ranges in the time range assigning unit.

Methods and systems for providing a video stream along with a slow motion video showing a particular event depicted in the video stream are described herein. The method includes generating a first video stream and generating a second video stream, which is a slow motion video stream, from the first video stream by modifying a playback speed of the first video stream. The method includes monitoring content of the first video stream to identify an event trigger of a predefined set of event triggers. Each event trigger indicates a presence in the first video stream of an event that is to be generated for display using the second video stream. The method includes determining, based on the identifying of the event trigger, to transmit the second video stream along with the first video stream, and simultaneously transmitting both the first video stream and the second video stream.

An electronic device according to one embodiment may comprise: a touch display; at least one processor including a processing circuit; and a memory for storing instructions. When executed individually or collectively by the at least one processor, the instructions enable: the electronic device to play back a video in a normal mode on a user interface through the touch display on the basis of a first user input for playing back the video, which is stored in the memory; and a second user input for playback in a slow motion mode to be acquired while the video is played back in the normal mode through the touch display. The second user input can correspond to a touch input on the touch display. When executed individually or collectively by the at least one processor, the instructions enable: interpolated frames to be generated by performing a frame rate conversion operation on corresponding frames included in the video, while the second user input is held on the touch display; the electronic device to play back the video in the slow motion mode by displaying the corresponding frames together with the generated interpolated frames through the touch display, while the second user input is held on the touch display; and the electronic device to resume, on the basis of the second user input being released from the touch display, the operation of playing back the video in the normal mode through the touch display.

A method for interpolating high resolution intermediate images is suggested. The method relies on an iterative approach exploiting in a current interpolation step additional information contained in up sampled intermediate images from a previous interpolation step. In this way the proposed method overcomes shortcomings of known interpolation methods regarding the interpolation of high-resolution images. A broadcast production system leveraging the proposed interpolation method allows for replay of scenes selected by a production director in slow-motion without requiring dedicated slow-motion cameras.

This invention discloses an adaptive temporal modeling-driven method and medium for human pose estimation in motion scenes. It constructs a 3D human pose estimation network model for motion scenes based on the speed of motion, utilizing physical constraint-based motion priors and the uncertainty of predicting 3D human joints to improve the model's robustness to motion scenes. Using human motion videos at different speeds as input, it first obtains the corresponding 2D human joint sequence based on an existing high-quality 2D human pose estimation model. This 2D human joint sequence is then input into the network model to obtain a trained model. This invention can adaptively adjust the receptive field according to the motion speed, using a small receptive field to capture instantaneous changes in fast motion and a large receptive field to capture long-term dependencies in slow motion, thus adapting to different motion speeds and improving the accuracy of human pose estimation in motion scenes at different speeds.

This application relates to the field of terminal AI technologies, and discloses a video shooting method and an electronic device. The electronic device disclosed in this application is provided with a first camera and a second camera. After receiving an instruction for shooting a slow motion video, the electronic device can invoke the first camera to perform preview, and after detecting that a target moving object moves in a field of view of the first camera, determine a target shooting frame rate. Further, the electronic device invokes the second camera to shoot a slow motion video of the target moving object at the target shooting frame rate. In this way, the electronic device can determine a best shooting frame rate based on a moving speed of the target moving object. This achieves a high degree of intelligence, and can optimize a shooting effect.

A method comprises receiving one or more indications corresponding to one or more derivative video files. Each derivative video file of the one or more derivative video files has a different frame rate. The method further comprises selecting an indication of a derivative video file with a corresponding derivative video frame rate. The method further comprises receiving the derivative video file and an original video frame rate. The method further comprises determining a playback frame rate to slow a derivative video of the derivative video file using a desired frame rate, the derivative video frame rate, and the original video frame rate. The method further comprises displaying the derivative video at the determined playback frame rate.

Provided are a method for detecting a highlight moment, an electronic device, and a non-transitory computer-readable medium. The electronic device captures a sequence of images of a field of view with a first frame rate, the sequence of images including at least an initiation of the highlight moment. In response to determining, based on at least a gray centroid of a region of interest (ROI) of one image of the sequence of images, that an object appears in the ROI of the sequence of images from the one image, the electronic device determines the one image as an initial image at which the highlight moment is initiated. The electronic device further stores multiple highlight images in association with the highlight moment in the memory of the electronic device. The stored highlight images correspond to the first frame rate.

Various embodiments provide an electronic device including: a camera comprising an image signal processor configured to process a video output from an image sensor; a memory; and a processor, wherein the processor is configured to: obtain the processed video from the image signal processor; extract a portion of the obtained video to detect motion; synchronize the obtained video with the extracted video, based on the motion detection; produce a slow motion video by converting a frame rate of the synchronized video; and encode the produced slow motion video and store the same in the memory, and a method thereof. Various embodiments may be provided.

A compensating timer system and method utilizable with video data featuring sections of different playback or recording speeds. The compensating timer system can be utilized with a user interface associated with and displayable thereon. The user interface can include a video display region configured or configurable to display video data, and an animated time indicator. The animated time indicator can be dependent on a modified playing speed of the video data that changes between different first and second speed rates. The first speed rate can be changed to the second speed rate upon receipt of an input associated with an affordance, by modifying at least one frame in the video data. This allows for continuous recording and / or displaying of video at different speed rates without altering operations or settings. The animated time indicator can be an animated affordance, an animated progress bar, an elapsed timer and / or a time remaining clock.

Methods and systems for providing a video stream along with a slow motion video showing a particular event depicted in the video stream are described herein. The method includes generating a first video stream and generating a second video stream, which is a slow motion video stream, from the first video stream by modifying a playback speed of the first video stream. The method includes monitoring content of the first video stream to identify an event trigger of a predefined set of event triggers. Each event trigger indicates a presence in the first video stream of an event that is to be generated for display using the second video stream. The method includes determining, based on the identifying of the event trigger, to transmit the second video stream along with the first video stream, and simultaneously transmitting both the first video stream and the second video stream.