71 results about "Stereoscopic video" patented technology

A display device presents volumetric content comprising a volumetric video. The volumetric video comprises a volumetric representation of one or more elements a three-dimensional space. Input indicative of a control operation associated with the presentation of the volumetric video is received. The presentation of the volumetric video by the display device is controlled by executing the control operation. While the control operation is being executed, the volumetric representation of the one or more elements of the three-dimensional space are displayed from multiple perspectives based on movement of a user.

Methods and systems for stereoscopic 3D video are described. Input HDR stereoscopic views in a first codeword representation are merged together by a first merging function to generate an input merged view to optimize a reshaping operation which generates a reshaped merged view in a second codeword representation and associated composer metadata. The reshaped merged view may be split and re-merged by a second frame packing function to optimize video encoding efficiency of an output coded bitstream based on the reshaped merged view. In a decoder, after extracting the reshaped merged view from the coded bitstream, a composer function applies the composer metadata to the decoded reshaped merge view to generate an output merged view in the first codeword representation. Then it generates output HDR stereoscopic views based on the output merged view.

In some embodiments, a method determines a disparity value from a plurality of disparity values in a current frame of a stereoscopic video. The disparity value is based on a difference of a value for a pixel between a first video and a second video of the stereoscopic video. A location is determined in a current frame that include the disparity value. The method analyzes first frames prior to the current frame to adjust disparity values in the first frames to generate one or more adjusted first disparity values. Also, the method analyzes second frames after the current frame to adjust disparity values in the second frames to generate one or more adjusted second disparity values. The one or more adjusted first disparity values and the one or more adjusted second disparity values are output for use in displaying captions in the first video or the second video.

The present disclosure relates to an image modification process used to generate a chosen type of stereoscopic video of the common field of view shared by two cameras without requiring any pre-set and arrangement normally needed for stereoscopic display. The process can use left and right video streams of images originating from a wide range of camera types sharing some portion of their respective fields of view that are not limited to a specific relative orientation (convergent, parallel or divergent) and can be used to adapt in real time the stereoscopic video to be displayed to a viewer where his dynamic inputs are constantly updated. The proposed method can be used to optimize, correct and or allow the use of various apparatuses (webcams, cameras, scanners, etc.) that may come out of the production lines with imperfects to the capture cameras.

The invention relates to the technical field of stereoscopic vision, and discloses a synchronous speed visual matching method and system, electronic equipment and a storage medium, and the method comprises the steps: synchronously collecting a stereoscopic video sequence with a predefined frame rate; executing multi-target hybrid tracking and motion induction detection, and outputting target motion information including position and velocity vectors; extracting hierarchical motion features of the target from continuous multiple frames of the stereoscopic video sequence, and performing unified space-time coding; under geometric constraints of stereoscopic vision, scale cosine similarity, direction similarity and trajectory consistency measurement are calculated and serve as observation evidences to be input into the probabilistic reasoning model for fusion, and a posterior probability representing matching reliability is output; the weight distribution of the speed similarity and the direction similarity is adjusted according to the motion characteristics of the targets in the scene, and the stable corresponding matching relation between the left view target and the right view target is established. According to the method, high-time-resolution information can be utilized, motion features and geometric constraints can be effectively fused, and the method has self-adaptive capacity.

Systems and methods are described for reducing thermal distortion in an optical display for use in a 3D stereoscopic video conferencing system. The thermal distortion can arise from operation of an array of LEDs in a back light unit of the display. Forming cut-outs in the display can interrupt the flow of heat to maintain geometric stability of precision cameras mounted to the display edges while also allowing sufficient heat dissipation paths for the LEDs. Structural reinforcement bars can be added, and an opaque film can be used to block light loss from the LEDs.

The present disclosure relates to an image correction process that is used to generate a selected type of stereoscopic video of a common field of view shared by two cameras without the need for pre - settings and arrangements normally required for stereoscopic display. This process can use the left and right video streams of images generated from a wide range of types of cameras that share some portion of the field of view of each camera, without being limited to a particular relative orientation, i.e., convergence, parallel, or divergence. Using this process, a stereoscopic video to be displayed to a viewer can be adapted in real - time with the viewer's dynamic input being constantly updated. Using the proposed method, various devices such as web cameras, cameras, scanners, etc. that may come out of a production line with imperfections in the capture cameras can be optimized, corrected, and / or made usable.

The invention provides a 4K3D surgical microscopic light path system. The 4K3D surgical microscopic light path system comprises a focusing module, a zoom module and a reflection module which are sequentially arranged on the same imaging light path from an object plane to an image plane, a 4K3D image processing module and a binocular eyepiece module which are coupled with the light path of the reflection module, and a self-adaptive illumination module independent of the imaging light path, the reflection module is used for transmitting the imaging light to the 4K3D image processing module and the binocular eyepiece module in a beam splitting manner, the 4K3D image processing module is used for generating the imaging light and outputting a stereoscopic video signal with 4K resolution, and the binocular eyepiece module is used for converting the imaging light into a physical natural image which can be observed in real time by binocular. According to the 4K3D operation microscopic optical path system disclosed by the invention, an operator can flexibly select electronic imaging observation or optical observation according to operation requirements.

The invention provides a stereoscopic video model training method and device, equipment, a medium and a program product, and relates to the technical field of computers, and the stereoscopic video model training method comprises the steps: obtaining a first prediction map and a depth map of the first prediction map according to a first stereoscopic video generation model and a first monocular map; the first stereoscopic video generation model is generated by training a first stereogram; generating a first loss function of the first encoder and the first decoder according to the first stereogram, the first monocular map, the first prediction map and a depth map of the first prediction map; and performing supervised training on the first encoder and the second encoder by using the first loss function to generate a second stereoscopic video generation model. According to the invention, the training data volume is increased, and the second stereoscopic video generation model is generated by using the first loss function, so that better scene understanding and more robust feature representation can be realized, and the video quality of the 3D video can be improved.

The invention discloses a stereoscopic video automatic separation and synchronization signal generation method and system based on an embedded identifier. A SyncMark synchronization mark is integrated on the basis of an original StereoMark scheme, stereo format description and synchronization parameters are embedded in a video coding layer at the same time through double SEI messages, and double backup is carried out on a container layer. And the playing end generates high-precision left and right frame synchronization signals according to the synchronization parameters, and outputs the high-precision left and right frame synchronization signals through interfaces such as HDMI VRR, DP Adaptive Sync and the like, so that the synchronization precision less than 1ms is realized. Adaptive network delay compensation and compatibility of multiple display devices are supported, and the 3D film watching experience is remarkably improved. The system is suitable for VR head-mounted display, vehicle-mounted 5D cabins, sports live broadcast and other scenes.

A model predicts the geometry of both visible and occluded traversable surfaces from input images. The model may be trained from stereo video sequences, using camera poses, per-frame depth, and semantic segmentation to form training data, which is used to supervise an image to image network. In various embodiments, the model is applied to a single RGB image depicting a scene to produce information describing traversable space of the scene that includes occluded traversable. The information describing traversable space can include a segmentation mask of traversable space (both visible and occluded) and non-traversable space and a depth map indicating an estimated depth to traversable surfaces corresponding to each pixel determined to correspond to traversable space.

The invention provides a video generation method and device, electronic equipment and a storage medium, and relates to the field of image processing, and the main technical characteristics comprise the following steps: responding to description information of a first image input by a user, carrying out semantic expansion on the description information, and generating a semantic description text containing a front and back depth-of-field relationship; generating a second image according to the first image and the semantic description text, and marking a key area corresponding to the description information in the second image; generating a dynamic video according to the second image; determining a pixel offset according to depth information of each frame in the dynamic video, and performing floating adjustment on a stereo parameter of the key area to generate a left-eye and right-eye parallax image; and generating a target video according to the left and right eye parallax image, thereby effectively improving the layering sense and stability of the 3D visual effect, meeting the stereoscopic visual experience requirement of a user, and highlighting the key point and spatial level of the stereoscopic video.

Systems and techniques are described herein for processing video data. For example, a machine-learning based stereo video coding system can obtain video data including at least a right-view image of a right view of a scene and a left-view image of a left view of the scene. The machine-learning based stereo video coding system can compress the right-view image and the left-view image in parallel to generate a latent representation of the right-view image and the left-view image. The right-view image and the left-view image can be compressed in parallel based on inter-view information between the right-view image and the left-view image, determined using one or more parallel autoencoders.

The invention provides a stereoscopic video compression method with double-branch attention. The stereoscopic video compression method comprises the following steps: dividing a stereoscopic video into a left video frame sequence and a right video frame sequence; inputting a video frame of the stereoscopic video at the t moment, a time adjacent reconstruction frame and a view adjacent reconstruction frame of the video frame into a DAN stereoscopic video compressor for compression to obtain a video reconstruction frame at the t moment; the DAN stereo video compressor comprises a feature extraction module, a motion estimation module, a parallax estimation module, an LGEDB-based coding and decoding module, a motion compensation module, a parallax compensation module, a double-branch high-frequency information fusion module and an image reconstruction module. The LGEDB and the DHFFM provided by the invention can be used for realizing image reconstruction with higher quality at the same or lower bit per pixel point (BPP).

A method for creating a combined representative 3D and stereoscopic video output for use within robotic surgery. A 3D model 116 of a patient is first visualised by a user device 118 and therein can be

Some multi-view video compression solutions fail to reduce cross-camera redundancy, or they only work for stereo-video with two source inputs. To address this, an element-wise video management approach is used to compress single and multi-view video streams. A four-dimensional scenario is decomposed into a background model and one or more foreground object models. The models fully compress across three-dimensional spatial dimensions and cross-camera redundancy and can be transmitted to a decoder offline or stored locally with the decoder. A decoder can render video frames based on one or more camera poses and one or more foreground object poses, which compress across the time dimension and take extremely low transmission bandwidth. To improve reconstruction of the video frame, a compressed residual can be transmitted to the decoder. The decoder can use the compressed residual to remove artifacts in a reconstructed frame.

The invention discloses a video fusion ecological environment monitoring system, and relates to the technical field of ecological environment monitoring. The system comprises a data acquisition module, a three-dimensional space registration module, a space service publishing module, a video fusion display module and a database module. The data acquisition module selects a video monitoring camera and captures a real-time monitoring video stream; the three-dimensional space registration module completes the space registration of the monitoring video and the three-dimensional scene by using a registration tool and a plurality of algorithm models; the space service publishing module is fused with the three-dimensional live-action three-dimensional model to complete service publishing; the video fusion display module realizes query display of an ecological service three-dimensional fusion scene and a monitoring video; and the database module provides data storage support. According to the invention, the problems of video picture isolation and three-dimensional scene static state in traditional monitoring are solved, and more intuitive and stereoscopic video data are provided for ecological environment management decision.

The embodiment of the invention belongs to the video processing technology, and provides video processing equipment, terminal equipment and a video processing method, and the video processing equipment comprises a processor which is used for generating a three-dimensional space model of a scene according to an obtained image of the scene where the video processing equipment is located; receiving scene real-time pictures acquired by a plurality of acquisition sub-modules in the acquisition module, wherein different acquisition sub-modules are located at different positions of a scene; generating a single-point stereoscopic video corresponding to the acquisition sub-module based on the scene real-time picture and the stereoscopic space model; the single-point stereoscopic video is a video of a current scene observed from the position of the acquisition sub-module; and sending the target stereoscopic video set obtained based on the single-point stereoscopic video of the plurality of acquisition sub-modules to the terminal equipment, so that the terminal equipment adjusts the picture form of the displayed scene based on the target stereoscopic video set and the operation of the user when the user operates, so that the displayed scene picture presents a stereoscopic effect, the field substitution sense is improved, and the user experience is improved. And the user experience is improved.

This disclosure provides techniques and apparatuses for displaying stereoscopic video data associated with different viewing angles of a target surgical site. An example ophthalmic imaging apparatus includes a first camera head mounted in a first orbital position above a target surgical site associated with an eye of a patient, wherein the first camera head includes at least one stereoscopic lens set providing a first viewing angle of the target surgical site. Additionally, the ophthalmic imaging apparatus includes at least a second camera head mounted in a second orbital position above the target surgical site, wherein the second camera head includes at least one additional stereoscopic lens set providing a second viewing angle of the target surgical site different from the first viewing angle of the target surgical site.

The invention provides a 3D stereoscopic video displaying and watching device and method, and the device comprises adjustable glasses which comprise two adjustable light-transmitting assemblies; the first display device is used for playing a 3D video; the display device comprises a display screen and a binocular picture light-transmitting plate covering the display screen; or the display device comprises a display screen, and a built-in left-eye and right-eye picture light-transmitting plate is embedded in the display screen; a picture of the stereoscopic video comprises a left part and a right part, the left part and the right part respectively represent a left eye view angle image and a right eye view angle image, and the left eye view angle image and the right eye view angle image are spliced together left and right to form a frame of image. The adjustable glasses are adopted to adjust the direction of the polarized light incident to the left and right eyes, and meanwhile, the polarized light assembly on the display terminal is combined, so that the left and right eyes can observe images respectively, and stereoscopic vision is formed. And the polarized lenses of the adjustable glasses can rotate, so that the polarized light direction of the display screen can be accurately aligned, and the watching effect is good.

The invention relates to the technical field of stereoscopic video signal processing and interactive television terminal energy efficiency management, and discloses an energy-saving interactive screen projection control system based on image perception, which is characterized in that a multi-channel load demand mapping unit analyzes an input signal flow into power demand space distribution of each node of a load network; the gradient threshold power isolation logic unit defines a power supply cut-off region according to the power gradient mutation characteristics; the distributed current injection regulator carries out truncation zero level operation on the load nodes in the cut-off region, and carries out time domain damping modulation on the non-cut-off region according to migration vector data. By constructing a differential power supply protocol of a physical level, the dynamic voltage stabilization precision of the core load nodes is ensured, and meanwhile, time domain damping modulation is carried out on the non-cut-off region according to the migration vector data. Redundant electric energy input of a low-demand background area is cut off, and the energy utilization efficiency of the interactive stereoscopic display system and the stability of video picture depth reconstruction are improved.

One aspect of this disclosure relates a video processing device comprising a processor for processing a manifest file for video streaming for a user. The manifest file comprises at least a plurality of positions defined for a scene that are associated with pre-rendered omnidirectional or volumetric video segments stored on a server system. The manifest file may also contain a plurality of resource locators for retrieving omnidirectional or volumetric video segments from the server system. Each resource locator may be associated with a position defined for the scene. The video processing device may be configured to associate a position of the user with a first position for the scene in the manifest file to retrieve a first omnidirectional or volumetric video segment associated with the first position using a first resource locator from the manifest file.

A method and apparatus for encoding stereoscopic video in patch-based atlas format in different length intra-periods is disclosed. A first atlas layout is constructed for a first sequence of 3D scenes. The number of 3D scenes in the sequence is chosen to fit the size of the GoP of the codec. A second sequence is iteratively built by appending the next 3D scene of the sequence when the number of patches of the layout constructed for the second sequence is less than or equal to the number of patches of the first layout. At the end of the iteration, one of the layouts is chosen to generate each atlas of the group. In this way, the size of the metadata is reduced and the compression is enhanced.

The mark-up apparatus includes a fiducial marking arrangement for being manually securely placed on a cable strain relief for visually distinctively marking the cable strain relief, a stereo camera for acquiring a live stereo video of an ultrasound scan probe scanning a patient's region of interest and a mark-up module for processing the live stereo video of the ultrasound scan probe scanning the patient's region of interest and overlaying navigation pointer mark-up(s) to the marked-up live video for instructing a human operator how to manipulate the ultrasound scan probe relative to the patient's region of interest.

According to an embodiment of the present disclosure, a method of generating a stereoscopic video includes: obtaining video data; extracting at least one multiple viewpoint video data from the video data; identifying an object associated with the video data; generating tracking information for the object based on the at least one multiple viewpoint video data; and performing rendering on the object based on a depth value corresponding to the tracking information.

The application relates to the technical field of video transmission, and discloses a stereoscopic video adaptive transmission method and system based on a video quality perception model, which comprises the following steps: obtaining stereoscopic video to be transmitted; performing point cloud downsampling processing on the stereoscopic video to obtain low-resolution point clouds; training a super-resolution model by using the low-resolution point clouds and the stereoscopic video; dividing the low-resolution point clouds by a server, and storing data information related to the low-resolution point cloud blocks; obtaining a prediction result of a user's viewpoint and network bandwidth; sending request information to the server according to the viewpoint and the prediction result; transmitting stereoscopic video blocks and the trained super-resolution model to a client according to the request information by using a video adaptive transmission algorithm based on the video quality perception model; receiving and assembling the stereoscopic video blocks, and processing complete stereoscopic video by using the trained super-resolution model to obtain high-quality 2D rendering pictures. The application can guarantee the video transmission quality under the condition of limited bandwidth, thereby improving the user experience.

The invention provides a medical endoscope 2D video real-time 3D conversion method based on deep learning, and belongs to the technical field of medical image processing. The medical endoscope 2D video real-time 3D conversion method based on deep learning comprises the following steps: preprocessing an original 2D endoscope video, including adaptive histogram equalization processing and specular reflection suppression; and carrying out depth estimation on the preprocessed video frame through a lightweight depth estimation network EndoDepthNet. And processing the continuous multi-frame video by using a motion recovery structure algorithm. And generating a binocular parallax image according to the optimized depth map, carrying out sub-pixel-level time sequence smoothing processing, and outputting a real-time 3D stereoscopic video. According to a deep learning model for endoscope scene optimization, multi-modal geometric constraint and hardware parallel optimization, the defects of a traditional method in precision, real-time performance and anti-interference capability are overcome.

A method for stereoscopic telestration in a 3D display system, and system therefore includes the steps of, and hardware for, aligning a telestration base plane to a reference object visible in a stereoscopic video stream; fusing a telestration overlay at the telestration base plane to ensure accurate depth alignment; and repositioning the telestration overlay to a moved telestration plane in front of or behind the telestration base plane by adjusting left and right eye overlays symmetrically. The repositioning may be performed without losing positional accuracy relative to the stereoscopic image stream.

A method and system for stereoscopic 3D video is described. Input HDR stereoscopic views of a first codeword representation are merged by a first merge function to generate an input merged view and optimize a reshaping operation to generate a reshaped merged view of a second codeword representation and associated composer metadata. The reshaped merged view can be split and remerged by a second frame packing function to optimize the video coding efficiency of a coded output bitstream based on the reshaped merged view. At a decoder, after extracting the reshaped merged view from the coded bitstream, a composer function applies the composer metadata to the decoded reshaped merged view to generate an output merged view of the first codeword representation. An output HDR stereoscopic view is then generated based on the output merged view.

1. The name of the design product: intelligent folding screen visualization device skeleton. 2. The use of the design product: LED display screen for stage art, three-dimensional video display. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.