A depth processing system includes a plurality of depth capturing devices and a host. The depth capturing devices are disposed around a specific region, and each generates a piece of depth information according to its own corresponding viewing point. The host combines a plurality of pieces of depth information generated by the plurality of depth capturing devices to generate a three-dimensional point cloud corresponding to the specific region according a relative space status of the plurality of depth capturing devices.

Systems and methods may provide for using one or more stereoscopic devices for gesture control and tracking in a head mounted display (HMD). Each of the one or more stereoscopic devices may include a pair of dynamic vision sensors (DVS) arranged to have complementary fields of view (FOV) to detect one or more of a leading and a trailing edge of an object moving in a range or area to be detected. The DVS sensors determine how the object is moving based on a change in light intensity of pixels without having to detect, transfer, or process all of the pixels. The system and method may thereby provide motion tracking and gesture control functions at very low latency and processing bandwidth.

A wearable electronic device with a display is provided. The wearable electronic device includes: a stereo camera configured to detect infrared light, a self-luminous display including a plurality of visible light pixels configured to output visible light corresponding to a virtual object image and a plurality of infrared pixels configured to output infrared light, an optical waveguide configured to output the virtual object image by adjusting a path of the visible light, a first control circuit configured to supply driving power and a control signal to the self-luminous display, and a second control circuit configured to supply driving power and a control signal to the stereo camera. The optical waveguide includes a half mirror configured to output reflected infrared light and transmitted infrared light in response to the output infrared light.

A method for calibrating at least one of the six-degrees-of-freedom of all or part of cameras in a formation positioned for scene capturing, the method comprising a step of initial calibration before the scene capturing. The step comprises creating a reference video frame which comprises a reference image of a stationary reference object. During scene capturing the method further comprises a step of further calibration wherein the position of the reference image of the stationary reference object within a captured scene video frame is compared to the position of the reference image of the stationary reference object within the reference video frame, and a step adapting the at least one of the six-degrees-of-freedom of a multiple cameras of the formation if needed in order to get an improved scene capturing after the further calibration.

Methods, apparatus, systems and articles of manufacture (e.g., physical storage media) to generate optical flow maps based on foreground and background image segmentation are disclosed. Example apparatus disclosed herein are to generate a reference optical flow map based on a stereo pair of background images corresponding to a first camera field-of-view and a second camera field-of-view, and generate a first optical flow map based on a stereo pair of input images corresponding to the first camera field-of-view and the second camera field-of-view. Disclosed example apparatus are also to combine the reference optical flow map and the first optical flow map based on an alpha matte to generate a second optical flow map associated with the stereo pair of input images, the alpha matte representative of segmentation of at least one of the stereo pair of input images into foreground and background regions.

According to one aspect of the teachings herein, a method and apparatus detect mechanical misalignments in a machine vision system during run-time operation of the machine vision system, and compensate image processing based on the detected misalignments, unless the detected misalignments are excessive. Excessive misalignments may be detected by determining a worst-case error based on them. If the worst-case error exceeds a defined limit, the machine vision system transitions to a fault state. The fault state may include disrupting operation of a hazardous machine or performing one or more other fault-state operations. Among the detected misalignments are internal misalignments within individual cameras used for imaging, and relative misalignments between cameras. The method and apparatus may further perform run-time verifications of focus and transition the machine vision system to a fault state responsive to detecting insufficient focal quality.

A system, method and apparatus for stereo vision with a plurality of coupled cameras and optional sensors.

Embodiments of the present application disclose various display control methods and apparatuses. One of the display control methods comprises: determining a first display area of a first light field display device and play sequence alignment reference information, wherein the first display area is used to play a first video; and controlling, according to the play sequence alignment reference information, a second display device to display, within at least one first frame interval of the first video, at least one second frame of a second video in the first display area, wherein the first video and the second video are different parts obtained by performing time-domain downsampling of a same content source. This solution can improve a gain of a time resolution actually displayed in a light field information content source, and improve the flexibility of time-domain display control.

A method includes obtaining a location of a viewpoint video to which a user currently pays attention in a multi-view video, obtaining a speed at which the user viewpoint switches to the location of the viewpoint video to which attention is currently paid, determining a quantity of predictive viewpoint videos (NNV) that need to be downloaded before the user switches to another viewpoint, determining locations of the predictive viewpoint videos in the multi-view video according to a preset rule and according to the location of the viewpoint video to which the user currently pays attention, the first speed, and the NNV, downloading the predictive viewpoint videos corresponding to the locations of the predictive viewpoint videos from a server end, and transmitting the predictive viewpoint videos.

The disclosure proposes a method and a system for 360-degree video playback. The method is applicable to a video playback system and includes at least the following steps. A current frame of a 360-degree video having a sequence of frames is received. Candidate objects in the current frame are detected, and a main object is selected from the candidate objects by using a selector recurrent neural network (RNN) model based on information of the candidate objects in the current frame. A viewing angle corresponding to the current frame is computed by using a regressor RNN model based on the main object in the current frame. The current frame is displayed on the screen according to the viewing angle.