Abstract: A modular omni-directional sensor array (MOSA) enclosure is provided for visual surveillance. The MOSA enclosure is disposable on an elevated position and includes a lower equipment module and an upper optical module. The equipment module contains electrical power and control electronics and is disposed on the elevated position from underneath. The optical module contains a plurality of cameras viewing radially outward. The optical module is disposed onto the equipment module from above.

Abstract: Methods are described herein for signaling information regarding different viewpoints in a multi-viewpoint omnidirectional media presentation. Techniques disclosed include receiving, from a server, information identifying groups of viewpoints, including information identifying a first group of viewpoints and a second group of viewpoints. And further receiving, from the server, information identifying one or more omnidirectional videos captured from respective viewpoints belonging to the first group and information identifying one or more omnidirectional videos captured from respective viewpoints belonging to the second group.

Abstract: A method of analyzing one or ejecta, specifically kinematic properties, resulting from a dynamic event. The method comprising using a single trigger, single image sensor three dimensional photography system comprising a first plurality of pulsed laser beams, a stage for the dynamic event to occur and be observed and where the first plurality of pulsed laser beams converge. The laser beams are recombined into a single pulsed laser beam after the stage for capture on the single image sensor to a subframe for each pulsed laser beam, the subframes being combined into a unique frame for each time step. The frames are analyzed with respect to time to determine the displacement, velocity and/or acceleration thereof.

Abstract: Provided are a point cloud encoding method and decoding method, and an encoder and a decoder. The encoding method comprises: processing attribute information of a target point in a point cloud, so as to obtain a predicted residual of the attribute information of the target point; quantizing the predicted residual on the basis of a quantized weight of the target point and a quantized stride of the target point, so as to obtain a quantized residual of the attribute information of the target point, wherein the quantized weight of the target point is the weight used when weighting the quantized stride of the target point; and encoding the quantized residual, so as to obtain a code stream.

Abstract: A holographic display and method for operating the holographic display can include: a holographic display operable in a plurality of modes, a computing system, and a sensor. The holographic display can option include a user interface device. Views displayed by the display can optionally be processed or modified based on a viewer pose relative to the display.

Abstract: Provided is a video decoding method including determining a displacement vector per unit time of pixels of a current block in a horizontal direction or a vertical direction, the pixels including a pixel adjacent to an inside of a boundary of the current block, by using values about reference pixels included in a first reference block and a second reference block, without using a stored value about a pixel located outside boundaries of the first reference block and the second reference block; and obtaining a prediction block of the current block by performing block-unit motion compensation and pixel group unit motion compensation on the current block by using a gradient value in the horizontal direction or the vertical direction of a first corresponding reference pixel in the first reference block which corresponds to a current pixel included in a current pixel group in the current block, a gradient value in the horizontal direction or the vertical direction of a second corresponding reference pixel in the sec

Abstract: One embodiment of the present invention sets forth a technique for deblocking video frames. The technique includes determining a filter length associated with a boundary between a first block and a second block included in the same video frame. The technique also includes computing a parameter value that minimizes a sum of squares of second derivatives associated with samples from the first block and second block that are adjacent to the boundary. The technique further includes determining a plurality of filter values based on the parameter value and the filter length, and applying a filter having the filter length and the filter values to additional samples within the first and second blocks to generate two filtered blocks corresponding to the first and second blocks. The technique additionally comprises generating a second video frame that includes the two filtered blocks.

Abstract: Methods, systems and apparatus for video processing including coding or decoding are described. One example method of video processing includes determining, for a conversion between a video region of a chroma component of a video and a bitstream of the video, a manner of applying a cross-component adaptive loop filtering (CC-ALF) operation to a first sample of the chroma component based on a position of a second sample associated with the first sample. The method also includes performing the conversion based on the determining.

Abstract: A method for generating an unobstructed bowl view of a vehicle that includes obtaining a plurality of images from a plurality of cameras disposed on the vehicle and determining a plurality of depth fields. The method further includes detecting a plurality of distorted objects in the plurality of images with a first machine-learned model that assigns a class distribution to the detected distorted object and estimating a distance of each distorted object from its associated camera using the plurality of depth fields. The method further includes assigning an object weight to each distorted object in the plurality of distorted objects and removing at least one distorted objects from the plurality of images. The method further includes replacing each of the at least one removed distorted objects with a representative background generated by a second machine-learned model and stitching and projecting the plurality of images to form the unobstructed bowl view.

Abstract: A method and apparatus for generating additional information used to reconstruct an additional image through steps of: generating information for movement compensation based on the original right image of the stereoscopic image and the previous frame of the right image; and generating first additional information for reconstructing the right image to a high resolution based on the original right image and the information for movement compensation are provided.

Abstract: Object There is the problem in the related art that the relationship between a patch size which is a unit of processing of a neural network and the sizes of input and output pictures is not clearly defined.

Abstract: An image coding device is provided with a determination unit which determines whether to apply an orthogonal transform to a transform block obtained by dividing a prediction difference signal indicating a difference between an input image and a predicted image or perform a transform skip by which the orthogonal transform is not applied, and an orthogonal transform unit which performs processing selected on the basis of the determination, the image coding device comprising a quantization unit which, when the transform skip is selected on the basis of the determination, quantizes the transform block using a first quantization matrix in which the quantization roughnesses of all elements previously shared with a decoding side are equal, and when the orthogonal transform is applied to the transform block on the basis of the determination, quantizes the transform block using the first quantization matrix or a second quantization matrix that is transmitted to the decoding side.

Abstract: Disclosed is an image sensor including a plurality of selection circuits each suitable for receiving two clock signals among an input clock signal and a plurality of delayed clock signals, and outputting, as each of a plurality of selection clock signals, one selection clock signal between the two clock signals on the basis of a control signal; and a plurality of buffer circuits suitable for generating the plurality of delayed clock signals on the basis of the plurality of selection clock signals outputted from the plurality of selection circuits.

Abstract: A head mounted display includes a display device having a display surface, an optical system configured to adjust a focal point of an eye of an observer to the display device, a driving mechanism configured to drive the display device, a line-of-sight detector configured to detect a line of sight of the observer, and a controller configured to control, based on an output from the line-of-sight detector, the driving mechanism so that an angle formed by the line of sight and the display surface falls within a preset allowable range with respect to 90° at an intersection point of the line of sight and the display surface.

Abstract: A wrist-mounted system for tracking hand poses includes one or more cameras mounted to a wearable band. In some examples, the one or more cameras are low profile and may be located less than 15 mm, and preferably less than 10 mm, of the wrist of the user. In some examples, a system includes a wearable band and one or more imaging sensors. The one or more imaging sensors are disposed to have a field of view that is anatomically distal when the wearable band is coupled to an arm of the user. The one or more imaging sensors each define an optical axis spaced from the wearable band of less than 15 mm, and preferably less than 10 mm. The image data may come from a single camera mounted on the back of the wrist which captures images of the surface contours of the back of the hand to infer hand poses and gestures.

Abstract: The present disclosure relates to method and apparatus for the estimation of an accurate multiplane image from a set of posed images. The accuracy of an MPI representation is measured by the performance of the views generated by it through inverse homography sampling and alpha compositing. A variable number of posed images at a possibly different resolution representative of scenes with arbitrary geometry are used as input of the system. A first level of three modules, possibly trained based on deep learning methods, is built for extracting view and scene features and color scores. Numerous levels of the same three modules may be built and organized in a structure where a level deals with down-scaled version of the posed images.

Abstract: This disclosure discloses lane line detection methods and devices. In an implementation, features extracted by different layers of the neural network are fused to obtain a fused second feature map, so that the second feature map obtained through fusion processing has a plurality of layers of features. The fused second feature map has a related feature of a low-layer receptive field and a related feature of a high-layer receptive field. Afterwards, an output predicted lane line set is divided into groups, where each predicted lane line in each group has an optimal prediction interval.

Abstract: The present disclosure provides a method for automated image acquisition and imaging processing. The method may include obtaining imaging information of an object. The method may include determining, based on the imaging information, at least target device positioning information of an imaging device. The method may include causing, based on the target device positioning information of the imaging device, the imaging device to be positioned to perform the image acquisition. The method may include providing, based on the inspection information, guidance information, the guidance information being configured to guide positioning of the object. The method may also include obtaining a target image from an imaging operation by the imaging device. Further, the method may include determining a target image processing algorithm of a medical image.

Abstract: Video coding methods and apparatuses are provided. A set of two or more pictures is coded. The set includes at least a first picture coded with a first spatial resolution, and a second picture coded with a second spatial resolution different from the first spatial resolution. The set of two or more pictures is stored in a decoded picture buffer based on corresponding spatial resolutions. The set of two or more pictures stored in the decoded picture buffer is used as a set of reference pictures for coding one or more successive pictures subsequent to the set of two or more pictures. The set of two or more pictures is incorporated into a reference picture list that contains pictures with at least two different spatial resolutions.

Abstract: A tire groove depth display method includes a grounded part extracting step, a groove depth calculating step, an image generating step, and a displaying step. The grounded part extracting step extracts a grounded part on a surface of a tread part of a tire as a plurality of areas sandwiching a tire groove. The groove depth calculating step calculates a depth of the tire groove between respective areas of the grounded part. The image generating step generates an image that shows the areas extracted by the grounded part extracting step and information on the depth of the tire groove calculated by the groove depth calculating step. The displaying step displays the image generated by the image generating step.