Abstract: Techniques for aligning and stabilizing images generated by an integrated stereo camera pair with images generated by a detached camera are disclosed. A first image is generated using a first stereo camera; a second image is generated using a second stereo camera; and a third image is generated using the detached camera. A first rotation base matrix is computed between the third and first images, and a second rotation base matrix is computed between the third and second images. The third image is aligned to the first image using the first rotation base matrix, and the third image is aligned to the second image using the second rotation base matrix. A first overlaid image is generated by overlaying the third image onto the first image, and a second overlaid image is generated by overlaying the third image onto the second image. The two overlaid images are parallax corrected and displayed.

Abstract: An encoding apparatus according to an embodiment includes a specifying unit, a first encoder and a second encoder. The specifying unit specifies a first original image signal included in an original image signal. The first encoder generates base image encoded data obtained by encoding the first original image signal by inter-frame prediction using a reference image signal. The second encoder generates standard encoded data obtained by encoding a second original image signal serving as the original image signal other than the first original image signal by the inter-frame prediction based on the base image encoded data.

Abstract: A decoder includes circuitry and memory coupled to the circuitry. The circuitry, in operation, generates a first coefficient value by applying a CCALF (cross component adaptive loop filtering) process to a first reconstructed image sample of a luma component, and clips the first coefficient value. The circuitry generates a second coefficient value by applying an ALF (adaptive loop filtering) process to a second reconstructed image sample of a chroma component, and clips the second coefficient value. The circuitry generates a third coefficient value by adding the clipped first coefficient value to the clipped second coefficient value, and decodes a third reconstructed image sample of the chroma component using the third coefficient value.

Abstract: Transform modes are derived for inter-predicted blocks using side information available within a bitstream. An inter-predicted encoded video block and side information are identified within a bitstream. Based on the side information, a trained transform is determined for inverse transforming transform coefficients of the inter-predicted encoded video block from amongst multiple trained transforms. The transform coefficients of the inter-predicted encoded video block are inverse transformed according to the trained transform to produce a prediction residual. A video block is reconstructed using the prediction residual and the reference frame. The video block is then output within an output video stream for storage or display. To determine the trained transforms, a learning model uses individual side information types and combinations of the individual side information types processed against a training data set.

Abstract: Techniques are described for improving video coding. For example, a first block of a picture included in an encoded video bitstream can be obtained. A second block of the picture can be determined as being coded (e.g., encoded) using a type of block-based quantized residual domain pulse code modulation (BDPCM) mode, such as vertical BDPCM mode or horizontal BDPCM mode. In the event the second block is coded using the vertical BDPCM mode, a vertical intra-prediction mode can be determined for an intra-prediction mode list for the first block. The vertical intra-prediction mode can be added to the intra-prediction mode list for the first block. In the event the second block is coded using the horizontal BDPCM mode, a horizontal intra-prediction mode can be determined for the intra-prediction mode list for the first block and the horizontal intra-prediction mode can be added to the intra-prediction mode list.

Abstract: In a case where an area which is a part of a captured image captured using a fisheye lens is designated, a generation unit generates a display image based on a position of the area designated in the captured image. The display image is an image in which the captured image is rotated about a predetermined position in the captured image so that a state of a subject included in the area becomes more erect. A display control unit causes the display image generated by the generation unit to be displayed on a display unit.

Abstract: A vehicle with sensor enabled features includes a vehicle frame, a windshield movable between a lowered position and a raised position where the windshield is coupled to the vehicle frame, and a forward sensor assembly coupled to the vehicle frame and including a sensor module disposed within a protective housing assembly. The protective housing assembly defines an open end and includes a front cover configured to removably couple to the protective housing assembly to selectively cover the open end. When the windshield is in the raised position, the windshield covers the open end to facilitate protecting the sensor module. When the windshield is in the lowered position, the front cover is configured to cover the open end to facilitate protecting the sensor module.

Abstract: A method of digitally boresighting includes finding a laser spot in a field of view of an imaging device that has an optical center, wherein the laser spot is generated by a laser, determining an offset vector between the laser spot in the field of view and the optical center, and correcting for boresight misalignment of the laser and imaging device in the image on a display using the offset vector.

Abstract: Provided is an inspection system that can reduce the burden of inspecting a detector provided on a transport vehicle that travels on a preset transport path. An inspection system 1 includes a projection surface 5F that is disposed at a position located within a detection range IE of a detector 3 in a state in which a transport vehicle 2 is present at an inspection location IP set on a transport path R, and onto which detection light IL projected by the detector 3 is projected, an image capturing device C that captures an image of the projection surface 5F, and a determination unit that determines at least one state selected from a position, a shape, and a light intensity of the detection light IL projected onto the projection surface 5F, based on an image captured by the image capturing device C.

Abstract: An encoder includes circuitry and memory. Using the memory, the circuitry: encodes an original image and decodes the original image encoded, to generate a first bitstream and a local decoded image; encodes supplemental information and decodes the encoded supplemental information, to generate a second bitstream and local decoded supplemental information; inputs data based on the local decoded image and the local decoded supplemental information to a post processing network which is a neural network, to cause a reconstructed image to be output from the post processing network, the reconstructed image corresponding to the original image and being to be used to encode a following original image which follows the original image; and concatenates the first bitstream and the second bitstream to generate a concatenated bitstream.

Abstract: A method of video decoding includes checking one or more video blocks in pre-defined relative positions compared to a first video block to derive a first set of candidates, wherein each of the first set of candidates is derived from corresponding motion information of the video blocks checked, checking, upon a determination that a number of the first set of candidates has not reached a predetermined limit, one or multiple tables to derive a second set of candidates, and processing the first video block based on a bitstream representation of the first video block and the constructed candidate list.

Abstract: An industrial visualization system generates and delivers virtual reality (VR) and augmented reality (AR) presentations of industrial facilities to wearable appliances to facilitate remote or enhanced interaction with automation systems within the facility. VR presentations can comprise three-dimensional (3D) holographic views of a plant facility or a location within a plant facility. The system can selectively render a scaled down view that renders the facility as a 3D scale model, or as a first-person view that renders the facility as a full-scale rendition that simulates the user's presence on the plant floor. Camera icons rendered in the VR presentation can be selected to switch to a live video stream generated by 360-degree cameras within the plant. The system can also render workflow presentations that guide users through the process of correcting detected maintenance issues.

Abstract: A method of perceptual video coding based on face detection is provided. The method includes calculating a bit allocation scheme for coding a light field video based on a saliency map of the face, calculating an LCU level Lagrange multiplier for coding a light field video based on a saliency map of the face and calculating an LCU level quantization parameter for coding a light field video based on a saliency map of the face.

Abstract: Picture coding and decoding methods, an encoder, a decoder and a storage medium are provided. The encoder, before performing coding processing according to a matrix-based intra prediction (MIP) mode, sets initial right shift parameters corresponding to different sizes and different MIP mode numbers as an uniform offset parameter, the offset parameter indicating a number of right shifting bits of a predicted value, and when performing coding processing according to the MIP mode, performs coding processing according to the offset parameter. The decoder, before performing decoding processing according to an MIP mode, sets initial right shift parameters corresponding to different sizes and different MIP mode numbers as an uniform offset parameter, the offset parameter indicating a number of right shifting bits of a predicted value, and when performing decoding processing according to the MIP mode, performs decoding processing according to the offset parameter.

Abstract: A three-dimensional data encoding method includes: determining whether to encode, using an octree structure, a current space unit among a plurality of space units included in three-dimensional data; encoding the current space unit using the octree structure, when it is determined that the current space unit is to be encoded using the octree structure; encoding the current space unit using a different method that is not the octree structure, when it is determined that the current space unit is not to be encoded using the octree structure; and appending, to a bitstream, information that indicates whether the current space unit has been encoded using the octree structure.

Abstract: According to the invention, an image sensor is disclosed. The image sensor may include a plurality of pixels. Each pixel of a first portion of the plurality of pixels may include a near-infrared filter configured to block red, green, and blue light; and pass near-infrared light. Each pixel of a second portion of the plurality of pixels may be configured to receive at least one of red, green, or blue light; and receive near-infrared light.

Abstract: A view system (100A, 100B) for a vehicle (1) has an image capture unit (10, 10A, 10B) for capturing image data of a portion around a vehicle (1), an image processing unit (20A, 20B) for processing the captured image data, and an image reproduction unit (30, 30A, 30B) for reproducing the processed image data. Included are an image sensor (11) and an optical element having a distortion curve. The image data are distorted dependent on the position of the image sensor according to the distortion curve. The image processing unit (20A, 20B) is adapted for taking at least one partial portion (12, 12?) from the image data of the image sensor (11), wherein the geometry of the partial portion (12, 12?) is dependent on the position of the partial portion (12, 12?) on the image sensor (11).

Abstract: An imaging system includes a plurality of cameras capable of capturing actual images. Of the plurality of cameras, a first camera detects first motion information about a main object. The second camera detects second motion information about the main object. The first camera determines motion information to be used based on the first motion information and the second motion information.

Abstract: The image analysis method may comprise the steps of: measuring a distance between a subject and an image analysis apparatus; outputting an image obtained by photographing the subject; selecting at least two feature points in the image of the photographed subject on the basis of information on the output feature points; calculating the relative size of the pre-stored original image of the subject on the basis of the measured distance; extracting feature points in the pre-stored original image of the subject, which correspond to the at least two selected feature points, on the basis of the calculated relative size; and comparing the image of the photographed subject with the original image on the basis of the selected feature points and the extracted feature points.

Abstract: A method of video decoding includes checking one or more video blocks in pre-defined relative positions compared to a first video block to derive a first set of candidates, wherein each of the first set of candidates is derived from corresponding motion information of the video blocks checked, checking, upon a determination that a number of the first set of candidates has not reached a predetermined limit, one or multiple tables to derive a second set of candidates, and processing the first video block based on a bitstream representation of the first video block and the constructed candidate list.