Abstract: The present disclosure describes devices and methods for generating RGB images from Bayer filter images using adaptive sub-pixel spatiotemporal interpolation. An electronic device includes a processor configured to estimate green values at red and blue pixel locations of an input Bayer frame based on green values at green pixel locations of the input Bayer frame and a kernel for green pixels, generate a green channel of a joint demosaiced-warped output RGB pixel from the input Bayer frame based on the green values at the green pixel locations, the kernel for green pixels, and an alignment vector map, and generate red and blue channels of the joint demosaiced-warped output RGB pixel from the input Bayer frame based on the estimated green values at the red and blue pixel locations, kernels for red and blue pixels, and the alignment vector map.

Abstract: A translation pen includes: a pen body; and an image collector, a first processor and a second processor that are disposed in the pen body. The image collector, the first processor and the second processor are arranged in sequence in an extending direction from a pen tip to a pen tail of the pen body, and are sequentially coupled to one another. The image collector is configured to collect an image of a target translation object and transmit the image of the target translation object to the first processor. The first processor is configured to preprocess the image of the target translation object and transmit the preprocessed image to the second processor. The second processor is configured to control the image collector to collect the image of the target translation object and control the first processor to preprocess the image of the target translation object.

Abstract: The invention relates to a device for superimposing known patterns, characteristic of a region, on (real) images of said region. The device comprises, a memory in which patterns are stored, which are representative of a selected region, of known position and orientation with relation to a common reference and processing means, for determining a pattern representative of the selected portion in the memory, on receipt of the designation of at least one portion of an observed image of the selected region, taken at a selected angle and at least one representative attribute of said region, taking account of the attribute selected, then superimposing the determined pattern on the selected portion of the image taking account of the selected angle.

Abstract: A method of decoding point cloud data comprises obtaining a bitstream that includes an arithmetically encoded syntax element indicating a vertical plane position of a planar mode of a node; and decoding the vertical plane position of the planar mode in the node, wherein decoding the vertical plane position of the planar mode comprises: determining a laser index of a laser candidate in a set of laser candidates, wherein the determined laser index indicates a laser beam that intersects the node; determining a context index based on whether the laser beam is above a first distance threshold, between the first distance threshold and a second distance threshold, between the second distance threshold and a third distance threshold, or below the third distance threshold; and arithmetically decoding the vertical plane position of the planar mode using a context indicated by the determined context index.

Abstract: Generating a table with at least one skewed row, skewed column, shifted row, or shifted column is described. A table generation system generates a table that includes cells arranged in a grid comprising rows and columns, and defines each cell using a grid address, a grid span, a grid angle, a string skew value, a string shift value, and a shift indicator for the cell. The table generation system may receive input modifying a grid angle for at least one row or column and generate a modified table by skewing cells included in the at least one row or column by the grid angle. The table generation system may additionally or alternatively receive input shifting at least one row or column by a string shift value and modify the display of the table by shifting the at least one row or column according to the string shift value.

Abstract: Disclosed are systems, apparatuses, and methods for and related to dynamic control of torque and or lateral thrust applied to a load suspended load on a suspension cable to thereby achieve a target orientation or position or to otherwise move with reduced self-induced cyclic motion, with better behavior, and or to respond to changes in the load or disturbance forces.

Abstract: A method for detecting boxes includes receiving a plurality of image frame pairs for an area of interest including at least one target box. Each image frame pair includes a monocular image frame and a respective depth image frame. For each image frame pair, the method includes determining corners for a rectangle associated with the at least one target box within the respective monocular image frame. Based on the determined corners, the method includes the following: performing edge detection and determining faces within the respective monocular image frame; and extracting planes corresponding to the at least one target box from the respective depth image frame. The method includes matching the determined faces to the extracted planes and generating a box estimation based on the determined corners, the performed edge detection, and the matched faces of the at least one target box.

Abstract: Rendering an avatar may include determining an expression to be represented by an avatar, obtaining a blood texture map associated with the expression, wherein the blood texture map represents an offset of coloration from an albedo map for the expression, and rendering the avatar utilizing the blood texture map.

Abstract: Systems, methods, apparatuses, and computer program products for providing multimodal emotion recognition. The method may include receiving raw input from an input source. The method may also include extracting one or more feature vectors from the raw input. The method may further include determining an effectiveness of the one or more feature vectors. Further, the method may include performing, based on the determination, multiplicative fusion processing on the one or more feature vectors. The method may also include predicting, based on results of the multiplicative fusion processing, one or more emotions of the input source.

Abstract: The present disclosure is related to systems and methods for orthosis design. The method includes obtaining a three-dimensional (3D) model associated with a subject. The method includes obtaining one or more reference images associated with the subject. The method includes determining, based on the 3D model and the one or more reference images, orthosis design data for the subject. The orthosis design data may be used to determine an orthosis for the subject.

Abstract: Methods and systems are described for registering a sports field to a video. Video of a live event may feature participants at a venue. A template of the venue, including virtual markings that represent real markings on the venue, may be obtained. A homographic transformation between an image plane and a ground plane may be determined by matching virtual markings to corresponding real markings captured in at least one frame of the video. The determined homographic transformation may be used in the automated analysis of sports statistics and in improving inserted annotations and visualizations.

Abstract: A method of decoding an image with latent feature-domain intra-prediction is performed by at least one processor and includes receiving a set of latent blocks and for each of the blocks in the set of latent blocks: predicting a block, based on a set of previously recovered blocks; receiving a selection signal indicating a currently recovered block, based on the selection signal performing one of (1) and (2): (1) generating a compact residual, a set of residual context parameters, a decoded residual, and generating a first decoded block; (2) generating a second decoded block, based on a compact representation block and a set of context parameters. The method further includes generating a set of recovered blocks comprising each of the currently recovered blocks; generating a recovered latent image by merging all the blocks in the set of recovered blocks; and decoding the recovered latent image, to obtain a reconstructed image.

Abstract: Embodiments relate to generating keypoint descriptors of the keypoints using a sub-scale refinement and a sample pattern radius adjustment. An apparatus includes a sub-pixel refiner circuit and a keypoint descriptor generator circuit. The sub-pixel refiner circuit determines a keypoint scale value for a scale dimension of a keypoint in an image pyramid by performing an interpolation of response map (RM) pixel values of a pixel block of RM images defined around the keypoint. The keypoint descriptor generator circuit determines sample scales of the image pyramid based on the keypoint scale value and determines a radius value for each sample scale based on the keypoint scale value. The keypoint descriptor generator circuit samples patches of pixel values at the sample scales using the radius value for each sample scale to generate a keypoint descriptor of the keypoint.

Abstract: Disclosed herein is a method for transmitting point cloud data, the method including encoding point cloud data, and transmitting a bitstream containing the point cloud data. Disclosed herein is a method for receiving point cloud data, the method including receiving a bitstream containing point cloud data, decoding the point cloud data, and rendering the point cloud data.

Abstract: Systems and methods for cuboid detection and keypoint localization in images are disclosed. In one aspect, a deep cuboid detector can be used for simultaneous cuboid detection and keypoint localization in monocular images. The deep cuboid detector can include a plurality of convolutional layers and non-convolutional layers of a trained convolution neural network for determining a convolutional feature map from an input image. A region proposal network of the deep cuboid detector can determine a bounding box surrounding a cuboid in the image using the convolutional feature map. The pooling layer and regressor layers of the deep cuboid detector can implement iterative feature pooling for determining a refined bounding box and a parameterized representation of the cuboid.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for escape detection and mitigation for aquaculture. In some implementations, a method includes obtaining one or more images that depict one or more fish within a population of fish that are located within an enclosure; providing, to one or more detection models configured to classify fish that are depicted within the images as likely being member or as likely not being member of a type of fish, the one or images; generating, as a result of providing the one or more images to the one or more detection models, a value that reflects a quantity of fish that are depicted in the images that are likely a member of the type of fish; and detecting a condition based at least on the value.

Abstract: Systems, apparatuses and methods may provide for technology that decodes data via an instruction that indicates a number of rulebooks to be processed, an input feature size, an output feature size, and a plurality of feature map base addresses, rearranges spatially distributed voxel output feature maps in the decoded data based on weight planes, and performs a channel-wise multiply-accumulate (MAC) operation on the rearranged spatially distributed voxel output feature maps to obtain an output, wherein the channel-wise MAC operation is performed as partial accumulations by a plurality of processing elements.

Abstract: Aspects of the disclosure provide methods and apparatuses for point cloud compression. In some examples, an apparatus for point cloud compression includes processing circuitry. The processing circuitry determines a plurality of original points in a point cloud that is quantized to a reconstructed position. The processing circuitry determines an attribute value of the reconstructed position based on attribute information of the plurality of original points. Further, the processing circuitry encodes the point cloud based on the determined attribute value of the reconstructed position.

Abstract: Aspects of the present disclosure provide techniques for document classification through signal processing. Embodiments include receiving a document for classification. Embodiments include generating an image of the document. Embodiments include producing a signal representation of the document based on numbers of non-white pixels in each horizontal scan line or vertical scan line of the image of the document. Embodiments include comparing the signal representation of the document to signal representations of previously-classified documents. Embodiments include determining, based on the comparing, a classification for the document. Embodiments include performing additional processing with respect to the document based on the classification for the document.

Abstract: A three-dimensional data encoding method includes: encoding first information of a first current node or second information of a second current node, the first current node being included in an N-ary tree structure of first three-dimensional points included in a first three-dimensional point cloud, N being 2 or 4, the second current node being included in an octree structure of second three-dimensional points included in a second three-dimensional point cloud. The encoding of the first information or the second information includes encoding the first information using a first encoding pattern including a pattern common to a second encoding pattern used in encoding the second information.