Abstract: A system and methods for a CODEC driving a real-time light field display for multi-dimensional video streaming, interactive gaming and other light field display applications is provided applying a layered scene decomposition strategy. Multi-dimensional scene data is divided into a plurality of data layers of increasing depths as the distance between a given layer and the plane of the display increases. Data layers are sampled using a plenoptic sampling scheme and rendered using hybrid rendering, such as perspective and oblique rendering, to encode light fields corresponding to each data layer. The resulting compressed, (layered) core representation of the multi-dimensional scene data is produced at predictable rates, reconstructed and merged at the light field display in real-time by applying view synthesis protocols, including edge adaptive interpolation, to reconstruct pixel arrays in stages (e.g. columns then rows) from reference elemental images.

Abstract: Subject matter regards generating a 3D point cloud and registering the 3D point cloud to the surface of the Earth (sometimes called “geo-locating”). A method can include capturing, by unmanned vehicles (UVs), image data representative of respective overlapping subsections of the object, registering the overlapping subsections to each other, and geo-locating the registered overlapping subsections.

Abstract: A method and apparatus of objective assessment of images captured from a human gastrointestinal (GI) tract are disclosed. According to this method, one or more images captured using an endoscope when the endoscope is inside the human gastrointestinal (GI) tract are received. Whether there is any specific target object is checked. When one or more specific target objects in the images are detected: areas of the specific target objects in the images are determined; an objective assessment score is derived based on the areas of the specific target objects in a substantial number of images from the images; where the step of detecting the specific target objects is performed using an artificial intelligence process.

Abstract: A camera parameter estimation apparatus: takes three sets of three-dimensional coordinates pertaining to an object and two-dimensional coordinates corresponding to the three-dimensional coordinates, and transforms a coordinate system of the three-dimensional coordinates from a world coordinate system to a local coordinate system; calculates a linear transformation matrix based on a projection transformation expression from the transformed three-dimensional coordinates to the two-dimensional coordinates, calculates a coefficient of a quartic equation pertaining to any one of depths from a camera center to each three-dimensional coordinate, and calculates each depth; calculates the rotation matrix in the local coordinate system using each depth and the linear transformation matrix; calculates a translation vector in the local coordinate system from each depth based on the projection transformation expression; and calculates a rotation matrix and a translation vector in the world coordinate system by performing

Abstract: The present disclosure provides a method and system for constructing a digital rock, and relates to the technical field of digital rocks. According to the method, a three-dimensional (3D) digital rock image that can reflect real rock information is obtained using an image scanning technology, and the image is preprocessed to obtain a digital rock training image for training a generative adversarial network (GAN). The trained GAN is stored to obtain a digital rock construction model. The stored digital rock construction model can be directly used to quickly construct a target digital rock image. This not only greatly reduces computational costs, but also reduces costs and time consumption for obtaining high-resolution sample images. In addition, the constructed target digital rock image can also reflect real rock information.

Abstract: Artefacts in a sequence of image frames may be reduced or eliminated through modification of an input image frame to match another image frame in the sequence, such as by geometrically warping to generate a corrected image frame with a field of view matched to another frame in sequence of frames with the image frame. The warping may be performed based on a model generated from data regarding the multi-sensor device. The disparity between image frames may be modeled based on image captures from the first and second image sensor for scenes at varying depths. The model may be used to predict disparity values for captured images, and those predicted disparity values used to reduce artefacts resulting from image sensor switching. The predicted disparity values may be used in image conditions resulting in erroneous actual disparity values.

Abstract: A system, method, and apparatus for generating a normalization of a single two-dimensional image of an unconstrained human face. The system receives the single two-dimensional image of the unconstrained human face, generates an undistorted face based on the unconstrained human face by removing perspective distortion from the unconstrained human face via a perspective undistortion network, generates an evenly lit face based on the undistorted face by normalizing lighting of the undistorted face via a lighting translation network, and generates a frontalized and neutralized expression face based on the evenly lit face via an expression neutralization network.

Abstract: A modular tracking system is described comprising of the network of independent tracking units optionally accompanied by a LIDAR scanner and/or (one or more) elevated cameras. Tracking units are combining panoramic and zoomed cameras to imitate the working principle of the human eye. Markerless computer vision algorithms are executed directly on the units and provide feedback to motorized mirror placed in front of the zoomed camera to keep tracked objects/people in its field of view. Microphones are used to detect and localize sound events. Inference from different sensor is fused in real time to reconstruct high-level events and full skeleton representation for each participant.

Abstract: A laundry appliance includes a basket rotatably mounted within a cabinet and defining a chamber configured for receiving a load of clothes, a water supply valve for regulating a flow of water into the chamber, and a camera assembly mounted within the cabinet in view of the chamber. A controller is configured to determine that the water supply valve is open to permit the flow of water into the chamber, identify an anticipated fog condition within the chamber based at least in part on the water supply valve being open, obtaining one or more images of the chamber using the camera assembly, analyzing the one or more images of the chamber to determine an actual fog condition in the chamber, and implementing a responsive action if the actual fog condition is different than the anticipated fog condition, e.g., providing a user notification.

Abstract: An electronic component evaluation method of evaluating a state of an electronic component includes acquiring reference point information, with respect to at least one terminal, reference point information including at least one of position information and first height information of a plurality of corresponding reference points on the terminal from imaging data obtained by image-capturing the electronic component including a component body and a plurality of terminals attached to the component body, and determining a state according to a shape of the electronic component based on a plurality of pieces of the reference point information.

Abstract: The present disclosure relates to an image registration method and a model training method thereof. The image registration method comprises obtaining a reference image and a floating image to be registered, performing image preprocessing on the reference image and the floating image, performing non-rigid registration on the preprocessed reference image and floating image to obtain a registration result image, and outputting the registration result image. The image preprocessing comprises performing, on the reference image and the floating image, coarse-to-fine rigid registration based on iterative closest point registration and mutual information registration. The non-rigid registration uses a combination of a correlation coefficient and a mean squared error between the reference image and the registration result image as a loss function.

Abstract: A method with video segmentation may include: acquiring, over time, a video sequence including a plurality of image frames, the plurality of image frames including a second image frame corresponding to a time t of the video sequence and a first image frame corresponding to a time t?1 before the time t; extracting a second feature vector from the second image frame; generating second hidden state information corresponding to the second image frame, based on first hidden state information corresponding to the first image frame and second fusion information in which the second feature vector is fused with information related to the second image frame stored in a memory; generating a second segmentation mask corresponding to the second image frame, based on an output vector corresponding to the second hidden state information; and outputting the second segmentation mask.

Abstract: A method for self-supervised depth and ego-motion estimation is described. The method includes determining a multi-camera photometric loss associated with a multi-camera rig of an ego vehicle. The method also includes generating a self-occlusion mask by manually segmenting self-occluded areas of images captured by the multi-camera rig of the ego vehicle. The method further includes multiplying the multi-camera photometric loss with the self-occlusion mask to form a self-occlusion masked photometric loss. The method also includes training a depth estimation model and an ego-motion estimation model according to the self-occlusion masked photometric loss. The method further includes predicting a 360° point cloud of a scene surrounding the ego vehicle according to the depth estimation model and the ego-motion estimation model.

Abstract: A computing system for wound tracking is disclosed herein. A server computing device receives a first image of a wound of a patient captured by a first camera. Subsequently, the server computing device receives a message generated by a computing device, the message indicating that a second camera of the computing device is to capture a second image of the wound. Responsive to receiving the message, the server computing device causes data to be transmitted to the computing device, the data based in part upon the first image. The data causes the computing device to present a semi-transparent overlay to a view of the wound on a display as perceived through a lens of the second camera, the semi-transparent overlay indicative of the first image. The computing device captures the second image via the second camera and causes the second image to be received by the server computing device.

Abstract: An image processing apparatus includes a low-resolution image generating circuit configured to generate a low-resolution image including a second pixel corresponding to first pixels based on an input image including the first pixels, and an edge preserving smoothing circuit configured to generate a reliability of the second pixel based on characteristics of values of the first pixels and perform edge preserving smoothing on the input image using a value of the second pixel of which a reflection ratio is adjusted, based on the reliability of the second pixel.

Abstract: Certain aspects involve video inpainting in which content is propagated from a user-provided reference video frame to other video frames depicting a scene. One example method includes one or more processing devices that performs operations that include accessing a scene depicting a reference object that includes an annotation identifying a target region to be modified in one or more video frames. The operations also includes computing a target motion of a target pixel that is subject to a motion constraint. The motion constraint is based on a three-dimensional model of the reference object. Further, operations include determining color data of the target pixel to correspond to the target motion. The color data includes a color value and a gradient. Operations also include determining gradient constraints using gradient values of neighbor pixels. Additionally, the processing devices updates the color data of the target pixel subject to the gradient constraints.

Abstract: The present application relates to an automated segmentation method for use with echocardiograms (echo). The method uses an iterative Dijkstra's algorithm, a strategic node selection, and a novel cost matrix formulation based on intensity peak prominence and is this termed the “Prominence Iterative Dijkstra's” algorithm, or ProID.

Abstract: Methods and systems for determining a surface color of a target surface under an environment with an environmental light source. A plurality of images of the target surface are captured as the target surface is illuminated with a variable intensity, constant color light source and a constant intensity, constant color environmental light source, wherein the intensity of the light source on the target surface is varied by a known amount between the capturing of the images. A color feature tensor, independent of the environmental light source, is extracted from the image data, and used to infer a surface color of the target surface.

Abstract: In one embodiment, a method includes receiving, by an object reconstruction module, a first image and a second image. The first image includes a first region of an object and the second image comprises a second region of the object. The method also includes identifying, by the object reconstruction module, a transitional image. The transitional image includes the first region of the object and the second region of the object. The method further includes determining, by the object reconstruction module, that the first region of the object in the transitional image and the first region of the object in the first image are equivalent regions and generating, by the object reconstruction module, a reconstruction of the object using the first image and the transitional image. The reconstruction of the object includes the first region of the object and the second region of the object and excludes equivalent regions.

Abstract: Described is a method for segmenting measurement data from measurement of an object that has at least one material transition region. The measurement data are used to generate a digital object representation that has the material transition region and a multiplicity of spatially resolved image information items relating to the object. The method may include: determining measurement data that have at least one small structure having an extent which is less than a predefined extent; determining at least two homogeneous regions in the measurement data and/or in the digital object representation, wherein at least one homogeneous regions has a small structure; analysing a local similarity of the multiplicity of spatially resolved image information items; adapting an extent of each homogeneous region until at least one border region is arranged at an expected position of a material transition region; and segmenting the digital object representation based on the adapted homogeneous regions.