Abstract: An example method of video coding includes receiving a video bitstream comprising a plurality of blocks and a plurality of quantized transform coefficients, and determining a quantized level for a quantized transform coefficient of the plurality of quantized transform coefficients. The method also includes selecting a quantizer from a set of three or more quantizers based on the quantized level, and deriving, using the selected quantizer, a dequantized transform coefficient for a first quantized transform coefficient of the plurality of quantized transform coefficients. The method further includes reconstructing a first block using the dequantized transform value.

Abstract: A video codec can involve determining a motion compensation mode associated with encoding a first block of picture information, the motion compensation mode including a sub-block based motion compensation prediction mode or a non-rectangular block partition mode; determining that a second block of picture information spatially neighboring the first block was encoded or decoded based on an illumination compensation; and encoding or decoding the first block based on the motion compensation mode and the illumination compensation.

Abstract: A method of decoding video data from a bitstream, the bitstream comprising video data corresponding to multiple slices, wherein the bitstream comprises a header comprising syntax elements to be used when decoding one or more slices; wherein the decoding comprising parsing the picture header, parsing at least one APS ID related syntax element prior to syntax elements relating to decoding tools; and decoding said bitstream using said syntax elements.

Abstract: In a method to improve backwards compatibility when decoding high-dynamic range images coded in a wide color gamut (WCG) space which may not be compatible with legacy color spaces, hue and/or saturation values of images in an image database are computed for both a legacy color space (say, YCbCr-gamma) and a preferred WCG color space (say, IPT-PQ). Based on a cost function, a reshaped color space is computed so that the distance between the hue values in the legacy color space and rotated hue values in the preferred color space is minimized. HDR images are coded in the reshaped color space. Legacy devices can still decode standard dynamic range images assuming they are coded in the legacy color space, while updated devices can use color reshaping information to decode HDR images in the preferred color space at full dynamic range.

Abstract: Method and computing device for inferring via a neural network environmental data of an area of a building based on visible and thermal images of the area. A predictive model generated by a neural network training engine is stored by the computing device. The computing device determines a visible image of an area based on data received from at least one visible imaging camera. The computing device determines a thermal image of the area based on data received from at least one thermal imaging device. The computing device executes a neural network inference engine, using the predictive model for inferring environmental data based on the visible image and the thermal image. The inferred environmental data comprise geometric characteristic(s) of the area, an occupancy of the area, a human activity in the area, temperature value(s) for the area, and luminosity value(s) for the area.

Abstract: A vehicle driver assist system includes a mounting bracket connectable with the vehicle and a camera housing connectable with the mounting bracket. One of the mounting bracket and the camera housing includes a channel for receiving a tab on the other of the mounting bracket and the camera housing. The tab on the other of the mounting bracket and the camera housing slides into the channel in the one of the mounting bracket and the camera housing to connect the camera housing to the mounting bracket. The one of the mounting bracket and the camera housing has a flexible member that engages the tab to damp movement of the housing relative to the mounting bracket.

Abstract: Disclosed is a method for encoding and decoding an image by applying different filtering strength to reference pixels based on a size relationship between a current block and each reference block such that a prediction block for the current block is constructed using reference pixels which are filtered adaptively according to their properties.

Abstract: A vehicular camera according to an aspect of an embodiment includes a substrate, a housing, and a conductive member. An imaging element is mounted on the substrate on. The housing has a first housing and a second housing made of metal. The housing accommodates the substrate in a space formed by the first housing and the second housing. The conductive member is disposed at a joint portion between the first housing and the second housing, and has conductivity. Any one or both of the first housing and the second housing have an insulating layer on a surface thereof.

Abstract: In a method to improve backwards compatibility when decoding high-dynamic range images coded in a wide color gamut (WCG) space which may not be compatible with legacy color spaces, hue and/or saturation values of images in an image database are computed for both a legacy color space (say, YCbCr-gamma) and a preferred WCG color space (say, IPT-PQ). Based on a cost function, a reshaped color space is computed so that the distance between the hue values in the legacy color space and rotated hue values in the preferred color space is minimized. HDR images are coded in the reshaped color space. Legacy devices can still decode standard dynamic range images assuming they are coded in the legacy color space, while updated devices can use color reshaping information to decode HDR images in the preferred color space at full dynamic range.

Abstract: A Tele folded camera operative to compensate for an undesired rotational motion of a handheld electronic device that includes such a camera, wherein the compensation depends on the undesired rotational motion and on a point of view of the Tele folded camera.

Abstract: A method includes receiving, by a processing device, a plurality of images of a test object, the plurality of images including a plurality of surfaces of the test object. The processing device selects a region of interest in each of the plurality of images, the region of interest comprising the test object having a background removed. For the plurality of regions of interest as selected, the method includes comparing, by the processing device, each region of interest with a corresponding profile image and identifying defects in each region of interest. The method includes grading, by the processing device, a cosmetic appearance of each region of interest based on the identified defects. The grades of the cosmetic appearance for each region of interest are stored.

Abstract: A security camera system includes a base unit and sensor modules for generating image data. The base unit includes several mounting sockets arranged at different elevational and azimuthal directions around the base unit, and the sensor modules attach, for example, magnetically, to the mounting sockets. Each mounting socket includes a socket ID, which is read by a reader module of the sensor modules and used to stitch together the image data from different sensor modules. The sensor modules are powered wirelessly via induction and communicate wirelessly with the base unit via wireless transceivers and antennas.

Abstract: Disclosed herein is a video decoding method including determining one or more adaptation parameter sets including a quantization matrix set including a plurality of quantization matrices, determining an adaptation parameter set including a quantization matrix set applied to a current picture or a current slice from among the one or more adaptation parameter sets, dequantizing transform coefficients of a current block of a current picture or a current slice based on the quantization matrix set of the determined adaptation parameter set, and reconstructing the current block based on the dequantized transform coefficients, wherein the adaptation parameter set includes coding information applied to one or more pictures or slices.

Abstract: A video decoding apparatus includes processing circuitry configured to perform operations comprising: receiving, from a video data stream, a sequence parameter set (SPS); parsing, from the SPS, an extra slice header bit map; mapping one or more bits in the extra slice header bit map to one or more flags that indicate presence or non-presence corresponding to a syntax element in a slice header; determining a number of extra slice header bits based on an amount of the one or more flags that indicate presence; and parsing, from the video data stream, the syntax element in the slice header based on the determined number of extra slice header bits.

Abstract: An image encoding/decoding method is provided. An image decoding method of the present invention may comprise restoring an intra-prediction mode of a current chroma block, deriving at least one representative value based on a neighboring sample of the current chroma block and a neighboring sample of a corresponding luma block corresponding to the current chroma block in case the intra-prediction mode is a CCLM (Cross-Component Linear Model) mode, deriving a parameter of CCLM by using the at least one representative value, and generating a prediction block of the current chroma block by using the parameter of CCLM.

Abstract: Disclosed are platforms, systems, methods, and media for performing networked video surveillance while preserving network bandwidth and performance by utilizing at least one video camera deployed on a quarantined sub-network, a local video recorder applying an edge computer vision algorithm to detect an area of an object above a threshold area, and one or more back-end applications applying one or more multi-stage hierarchical computer vision models to the uploaded recorded video to tag video with one or more identified classes of objects.

Abstract: Systems and techniques are described for image signal processor motion detection. In various examples, first image data including pixel values may be generated, where each pixel value is associated with a respective color tag of a color filter array. A first set of the pixel values corresponding to a first block may be determined. A second set of pixel values may be determined based on a respective pixel value of the first set and the respective color tag associated with that respective pixel value. A first intensity value associated with the first block may be determined based on the second set of pixel values. A second intensity value associated with a reference block may be determined. A comparison value representing a difference between the first intensity value and the second intensity value may be determined. A signal indicating detected motion may be sent based on the comparison value.

Abstract: Methods and systems are provided for a microscope system. In one example, a method for image-based detection of optical alignment for the microscope system comprises acquiring a plurality of contrast samples of a field of view of a subject, determining a contrast distribution for a plurality of divided sub-regions for the field of view based on the plurality of contrast samples, and generating an amount of angular discrepancy based on an in-focus position derived from the contrast distribution for each of the plurality of divided sub-regions. In one example, the method further comprises adjusting the microscope system based on the amount of angular discrepancy.

Abstract: A sensor assembly includes one or more sensors configured to collect data from an environment. A sensor window is disposed in a field of view of the sensor, such that the sensor senses the environment through the sensor window to generate sensor data. The sensor window is rotated relative to the sensor to cause obstructions on the sensor window, like water or debris, to disperse.

Abstract: A vehicular camera includes a cap having a barrel portion disposed to an outer circumference of a lens barrel and a second edge portion. At least a part of the second edge portion overlaps the circumference of the first lens and overlaps the first edge portion. Each of the plurality of protrusions is oriented from the barrel portion of the cap toward the optical axis, and protrudes along the first surface of the first lens. A first protrusion and a second protrusion are disposed adjacent to each other. A part of the first protrusion overlaps the first edge portion, and a part of the second protrusion overlaps the first edge portion. A first top portion and a second top portion are closer to the optical axis than the first edge portion, and the first surface of the first lens is exposed between the first and second top portions.