Provided are an apparatus and method for sensing a moving ball, which extract a feature portion such as a trademark, a logo, etc. indicated on a ball from consecutive images of a moving ball, acquired by an image acquisition unit embodied by a predetermined camera device, and calculate a spin axis and spin amount of rotation the moving ball based on the feature portion and thus spin of the ball is simply, rapidly, and accurately calculated with low computational load, thereby achieving rapid and stable calculation of the ball in a relatively low performance system. The sensing apparatus includes an image acquisition unit for acquiring consecutive images, an image processing unit for extracting a feature portion from the acquired image, and a spin calculation unit for calculating spin using the extracted feature portion.

Radar, lidar, and other active 3D imaging techniques require large, heavy sensors that consume lots of power. Passive 3D imaging techniques based on feature matching are computationally expensive and limited by the quality of the feature matching. Fortunately, there is a robust, computationally inexpensive way to generate 3D images from full-motion video acquired from a platform that moves relative to the scene. The full-motion video frames are registered to each other and mapped to the scene coordinates using data about the trajectory of the platform with respect to the scene. The time derivative of the registered frames equals the product of the height map of the scene, the projected angular velocity of the platform, and the spatial gradient of the registered frames. This relationship can be solved in (near) real time to produce the height map of the scene from the full-motion video and the trajectory.

A video decoding method that includes: receiving information for deriving motion information of a current block; deriving the motion information of the current block based on the received information for deriving the motion information; and performing prediction to generate predicted pixels of the current block based on the motion information of the current block, wherein the motion information of the current block is determined by using motion information of a reference block, wherein the reference block is determined based on a specific disparity vector, wherein the specific disparity vector is determined for an area in a picture to which the current block belongs, wherein the area which the specific disparity vector is determined is split based on a quad tree structure, and wherein the current block is a block of a texture picture and the reference block is a block in a reference view is disclosed.

A method for displaying virtual content to a user, the method includes determining an accommodation of the user's eyes. The method also includes delivering, through a first waveguide of a stack of waveguides, light rays having a first wavefront curvature based at least in part on the determined accommodation, wherein the first wavefront curvature corresponds to a focal distance of the determined accommodation. The method further includes delivering, through a second waveguide of the stack of waveguides, light rays having a second wavefront curvature, the second wavefront curvature associated with a predetermined margin of the focal distance of the determined accommodation.

A scanning camera for capturing images along two or more curved scan paths, the scanning camera comprising a camera assembly associated with each scan path, each camera assembly comprising an image sensor and a lens; a scanning mirror; and a drive coupled to the scanning mirror; wherein the drive is operative to rotate the scanning mirror about a spin axis according to a spin angle; the spin axis is tilted relative to each camera optical axis; the scanning mirror is tilted relative to the spin axis and each camera optical axis; the scanning mirror is positioned to reflect an imaging beam into each lens in turn; and each image sensor is operative to capture each image along a respective one of the scan paths by sampling the imaging beam at a corresponding spin angle.

Disclosed are methods and apparatuses for image data encoding/decoding. A method of decoding an image includes receiving a bitstream in which the image is encoded; obtaining index information for specifying a block division type of a current block in the image; and determining the block division type of the current block from a candidate group pre-defined in the decoding apparatus. The candidate group includes a plurality of candidate division types, including at least one of a non-division, a first quad-division, a second quad-division, a binary-division or a triple-division. The method also includes dividing the current block into a plurality of sub-blocks; and decoding each of the sub-blocks with reference to syntax information obtained from the bitstream.

A stereo camera apparatus includes a stereo camera, a speed sensor, and a control device. The control device includes one or more processors and one or more storage media. The one or more processors are configured to: detect corresponding points from a first image pair and a second image pair to be captured at different times by the stereo camera; divide each of images of the first image pair and the second image pair into regions; calculate, for each of the regions, a movement speed based on an external parameter by using one or more of the corresponding points included in the each of the regions; and calculate, for the each of the regions, a parallax correction value to cause a difference between the movement speed based on the external parameter and a movement speed detectable by the speed sensor to fall below a predetermined threshold.

A CNN operates on the disparity or motion outputs of a block matching hardware module, such as a DMPAC module, to produce refined disparity or motion streams which improve operations in images having ambiguous regions. As the block matching hardware module provides most of the processing, the CNN can be small and thus able to operate in real time, in contrast to CNNs which are performing all of the processing. In one example, the CNN operation is performed only if the block hardware module output confidence level is below a predetermined amount. The CNN can have a number of different configurations and still be sufficiently small to operate in real time on conventional platforms.

Disclosed are methods and apparatuses for image data encoding/decoding. A method of decoding an image includes receiving a bitstream in which the image is encoded; obtaining index information for specifying a block division type of a current block in the image; and determining the block division type of the current block from a candidate group pre-defined in the decoding apparatus. The candidate group includes a plurality of candidate division types, including at least one of a non-division, a first quad-division, a second quad-division, a binary-division or a triple-division. The method also includes dividing the current block into a plurality of sub-blocks; and decoding each of the sub-blocks with reference to syntax information obtained from the bitstream.

A method for intelligently measuring vehicle speed based on a binocular stereo vision system includes: training a Single Shot Multibox Detector neural network to obtain a license plate recognition model; calibrating the binocular stereo vision system to acquire parameters of two cameras; detecting the license plates in the captured video frames with the license plate recognition model, locating the license plate position; performing feature point extraction and stereo matching by a feature-based matching algorithm; screening and eliminating the matching point pairs, and reserving the coordinates of the matching point pair closest to the license plate center; performing stereo measurement on the screened matching point pair to get the spatial coordinates of the position; calculating and obtaining the speed of the target vehicle. The present invention is easy to install and adjust, could simultaneously recognize multiple trained features automatically, and better suit the intelligent transportation networks and IoT (Internet of Things).