Abstract: A method of an inter prediction process performed by a processing unit of a coding system comprises deriving combined linear combination parameters from two sets of linear combination parameters, where a first set of linear combination parameters is independent from the position of the to-be-predicted block and a second set of linear combination parameters depends on the position of the to-be-predicted block; and obtaining the value of the to-be-predicted sample using the combined linear combination parameters and predicted values of at least two samples belonging to different reference blocks of the to-be-predicted block.

Abstract: A display device according to an embodiment of the present disclosure includes: a transparent screen; one or more imaging units; and a video projection unit that acquires positional information regarding a predetermined subject included in each of captured images obtained by the one or more imaging units and then irradiates the transparent screen with video light on the basis of the positional information to cause predetermined video to appear on the transparent screen for the subject.

Abstract: A differential video rendering system, including a graphics processing unit (GPU); a graphical display coupled to the GPU; a video decoder configured to decode a bitstream of encoded data into a plurality of sets of decoded blocks; at least one processor configured to: generate, based on a first set of the plurality of sets of decoded blocks, a first differential video frame comprising a plurality of sets of differential regions, normalize each set of the plurality of sets of differential regions to a fixed size block to provide a normalized plurality of sets of differential regions, map a respective set of the normalized plurality of sets of differential regions to align with a respective tile size region of a plurality of tile size regions conforming with the GPU, generate a hierarchal region tree based on the normalized plurality of sets of differential regions mapped to the plurality of tile size regions, and generate a plurality of optimal regions based on the hierarchal region tree satisfying a predefin

Abstract: The invention provides a method for intelligently measuring vehicle trajectory based on a binocular stereo vision system, including the following steps: inputting a dataset into an SSD (Single Shot Multibox Detector) neural network to train a license plate recognition model; calibrating the binocular stereo vision system, and recording videos of moving target vehicles; detecting the license plates in the video frames with the license plate recognition model; performing stereo matching on the license plates in the subsequent frames of the same camera and in the corresponding left-view and right-view video frames by a feature-based matching algorithm; reserving correct matching point pairs after filtering with a homography matrix; screening the reserved matching point pairs, and reserving the one closest to the license plate center as the position of the target vehicle in the current frame; performing stereo measurement on the screened and reserved matching point pairs to get the spatial position coordinates of

Abstract: Fluorescence imaging with reduced fixed pattern noise is disclosed. A method includes actuating an emitter to emit a plurality of pulses of electromagnetic radiation and sensing reflected electromagnetic radiation resulting from the plurality of pulses of electromagnetic radiation with a pixel array of an image sensor to generate a plurality of exposure frames. The method includes applying edge enhancement to edges within an exposure frame of the plurality of exposure frames. The method is such that at least a portion of the plurality of pulses of electromagnetic radiation emitted by the emitter comprises one or more of electromagnetic radiation having a wavelength from about 770 nm to about 790 nm; or from about 795 nm to about 815 nm.

Abstract: A photographing method and an electronic device are provided, so that a to-be-photographed target can continue to be tracked after the to-be-photographed target returns to a shooting image, to improve accuracy of focusing performed during photographing of a moving object. The method includes: displaying a first image including a first object and a tracking indicator that is associated with the first object, the tracking indicator indicating that the first object is a tracked target; displaying a second image that does not include the first object or the tracking indicator; displaying a third image including the first object; automatically setting the first object as the tracked target and displaying the tracking indicator associated with the first object; and automatically focusing on the first object when displaying the third image.

Abstract: Disclosed is a nighttime road fog detection system. More specifically, the present invention relates to a nighttime road fog detection system which rapidly and accurately detects the time of occurrence of nighttime fog that occurs at dawn before sunrise using open information of closed-circuit television (CCTV) cameras installed on a road and a detection method thereof. According to an embodiment of the present invention, in a mapping image obtained by masking a fog region identified by a fog detection program on an image signal, a region incorrectly determined due to a whitening phenomenon caused by an external light source generated at night is corrected, and thus information about the fog region is more accurately provided.

Abstract: In some embodiments, an imaging system is provided. The imaging system comprises an image sensor, a light source, control circuitry, and function logic. The image sensor comprises a pixel array that includes a plurality of polarization pixel cells and a plurality of time-of-flight pixel cells. The light source is configured to emit light pulses to an object. The control circuitry is coupled to the light source and the pixel array, and is configured to synchronize a timing of the emission of the light pulses with sensing of photons reflected from the object by the plurality of time-of-flight pixel cells to generate depth information. The function logic is configured to determine a set of ambiguous surface normals using signals generated by the plurality of polarization pixel cells, and to disambiguate the set of ambiguous surface normals using the depth information to generate a three-dimensional shape image.

Abstract: Autonomous aerial navigation in low-light and no-light conditions includes using night mode obstacle avoidance intelligence, training, and mechanisms for vision-based unmanned aerial vehicle (UAV) navigation to enable autonomous flight operations of a UAV in low-light and no-light environments using infrared data.

Abstract: Various embodiments disclosed herein describe an infrared (IR) imaging system for detecting a gas. The imaging system can include an optical filter that selectively passes light having a wavelength in a range of 1585 nm to 1595 nm while attenuating light at wavelengths above 1600 nm and below 1580 nm. The system can include an optical detector array sensitive to light having a wavelength of 1590 that is positioned rear of the optical filter.

Abstract: Embodiments for automatic data preprocessing for a machine learning operation by a processor. For each data instance in a set of data instances, a sequence of actions may be automatically learned in a reinforcement learning environment to be applied for preprocessing each data instance separately. Each of the data instances may be preprocessed for use by one or more machine learning models according to the learned sequence of actions.

Abstract: Certain aspects provide a method for determining a solution to a combinatorial optimization problem, including: determining a plurality of subgraphs, wherein each subgraph of the plurality of subgraphs corresponds to a combinatorial variable of the plurality of combinatorial variables; determining a combinatorial graph based on the plurality of subgraphs; determining evaluation data comprising a set of vertices in the combinatorial graph and evaluations on the set of vertices; fitting a Gaussian process to the evaluation data; determining an acquisition function for vertices in the combinatorial graph using a predictive mean and a predictive variance from the fitted Gaussian process; optimizing the acquisition function on the combinatorial graph to determine a next vertex to evaluate; evaluating the next vertex; updating the evaluation data with a tuple of the next vertex and its evaluation; and determining a solution to the problem, wherein the solution comprises a vertex of the combinatorial graph.

Abstract: A device and a method for training a model including a first sub-model and a second sub-model. Digital data are down-scaled to generate first input data. The digital data are divided into multiple data areas to generate second input data. A first sub-model generates first sub-model data relating to first input data fed to it. The first sub-model data are up-scaled to form first output data. A second sub-model for the data areas generates corresponding output data areas relating to second input data fed to it. The output data areas are assembled to form second output data. The first and second output data are combined to form third output data. The first sub-model is trained on the digital data by comparing provided target data and the first output data. The second sub-model is trained on the digital data by comparing the target data and the third output data.

Abstract: A mobile electronic device includes a first camera configured to capture a first image of a subject in a first field of view and including an RGB array, a second camera configured to capture a second image of the subject in a second field of view that is different from the first field of view and including an RGBW array; and an image processor configured to generate a target image using at least one of the first or second images in accordance with a selected mode of a plurality of modes. The plurality of modes includes still image modes and video modes associated with separate, respective combinations of output speed and bit depth such that the image processor is configured to control an output of the second camera to have a different combination of output speed and bit depth based on the selected mode.

Abstract: A method for automatic generation of calibration parameters for a surround view (SV) camera system is provided that includes capturing a video stream from each camera comprised in the SV camera system, wherein each video stream captures two calibration charts in a field of view of the camera generating the video stream; displaying the video streams in a calibration screen on a display device coupled to the SV camera system, wherein a bounding box is overlaid on each calibration chart, detecting feature points of the calibration charts, displaying the video streams in the calibration screen with the bounding box overlaid on each calibration chart and detected features points overlaid on respective calibration charts, computing calibration parameters based on the feature points and platform dependent parameters comprising data regarding size and placement of the calibration charts, and storing the calibration parameters in the SV camera system.

Abstract: A video coding mechanism includes receiving a bitstream comprising a current picture including a sub-picture coded according to inter-prediction. Coded blocks contain candidate motion vectors for a current block of the sub-picture. The coded blocks include a collocated block from a different picture. A candidate list of candidate motion vectors for the current block are derived by excluding collocated motion vectors from the candidate list when the collocated motion vectors are included in the collocated block, when the collocated motion vectors point outside of the sub-picture, and when a flag is set to indicate the sub-picture is treated as a picture. A current motion vector for the current block is determined from the candidate list of candidate motion vectors. The current block is decoded based on the current motion vector. The current block is forwarded for display as part of a decoded video sequence.

Abstract: An apparatus for intraoral scanning comprises an elongate handheld wand comprising a probe at a distal end, one or more light projectors, and two or more cameras. Each light projector comprises at least one light source configured to generate light and a pattern generating optical element configured to generate a pattern of light when the light is transmitted through the pattern generating optical element. Each camera comprises a camera sensor and one or more lenses and is configured to capture a plurality of images that depict at least a portion of the projected pattern of light on an intraoral surface, wherein each camera is configured to focus at an object focal plane that is located between about 1 mm and about 30 mm from a lens of the one or more lenses that is farthest from the camera sensor.

Abstract: The method and system disclosed herein presents a method and system for capturing, by a camera device on a mobile robot moving in an environment, an image frame at a first location within a portion of the environment. In accordance with a determination that the image frame contains a first visual marker: the method includes determining a camera orientation angle from the camera device to a first anchor associated with the first visual marker based on the image frame; detecting, by a detector on the mobile robot, a first beacon signal emitted by the first anchor. The method includes determining a distance between the mobile robot and the first anchor; and determining an orientation angle of the mobile robot based on the camera orientation angle, and the distance between the mobile robot and the first anchor.

Abstract: A structured light projection module, a depth camera, and a method for manufacturing the structured light projection module are provided. The module comprises: a light source, comprising a plurality of sub-light sources that are arranged in a two-dimensional array and configured to emit two-dimensional patterned beams corresponding to the two-dimensional array, and the two-dimensional patterned beams comprising two-dimensional patterns; a lens, receiving and converging the two-dimensional patterned beams; and a diffractive optical element, receiving the two-dimensional patterned beams converged and emitted from the lens, and projecting speckle patterned beams corresponding to speckle patterns. The speckle patterns comprise a plurality of image patterns corresponding to the two-dimensional patterns, and the image patterns are rotated by an angle such that edges of the image patterns are not in parallel with a baseline between the structured light projection module and a capture module.

Abstract: A measurement apparatus operable to perform measurement concerning a predetermined item for a target subject which is a measurement target. The apparatus comprises an acquisition unit configured to, for a captured image acquired by capturing of an image capturing range that includes the target subject, acquire distance information indicating a distribution of a subject distance from an image capturing apparatus that performed the capturing and, at least, normal line information that indicates a normal line of a surface of the target subject; and a presentation unit configured to present a notification that indicates an image capturing direction of the image capturing apparatus for performing measurement of the predetermined item based on the normal line information acquired by the acquisition unit.