Abstract: A video encoding method includes (i) determining a current bit rate of a communication channel between a destination device and a source device that stores an input video frame, and (ii) generating a current reconstructed frame and an encoded bitstream at least in part via inter-frame coding of a current input video frame of a sequence of input video frames using a previously-generated reconstructed frame generated at least in part via inter-frame coding of a previous input video frame. The current reconstructed frame is a compressed version of the current input video frame. When both (i) a subsequent bit rate, determined after said inter-frame coding, is less than a threshold and (ii) the current bit rate exceeds the threshold, the method includes: (a) generating a downscaled reconstructed frame at least in part by downscaling the current reconstructed frame; and (b) appending the encoded bitstream with a bit sequence representing the downscaled reconstructed frame.

Abstract: A video processing method is provided, including: performing a conversion between a coded representation of a video including one or more video regions and the video, wherein the coded representation includes reshaping model information applicable for in-loop reshaping (ILR) of some of the one or more video regions, wherein the reshaping model information provides information for a reconstruction of a video unit of a video region based on a representation in a first domain and a second domain and/or scaling chroma residue of a chroma video unit, wherein the reshaping model information includes a parameter set that includes a first syntax element that derives a number of bits used to represent a second syntax element specifying an absolute delta codeword value from a corresponding bin, and wherein the first syntax element has a value smaller than a threshold.

Abstract: A method for in-loop sample offset filtering in a video decoder is disclosed. The method includes obtaining at least one statistical property associated with reconstructed samples of at least a first color component in a current reconstructed data block of a video stream, selecting a target sample offset filter among a plurality of sample offset filters based on the at least one statistical property, the target sample offset filter comprising a nonlinear mapping between sample delta measures and sample offset values, and filtering a current sample in a second color component of the current reconstructed data block using the target sample offset filter and reference samples in a third color component of the current reconstructed data block to generate a filtered reconstructed sample of the current sample.

Abstract: Disclosed herein are representative embodiments of generating representative motion information that can be used during processing of a video frame. In one exemplary embodiment disclosed herein, a reference frame comprising a group of blocks is processed, and motion information for the group of blocks is compressed at least by buffering representative motion-vector information and representative reference-frame index information for the group of blocks. The representative reference-frame index information comprises reference-frame index information of a representative block of the group of blocks, and the representative reference-frame index information represents reference-frame index information for the group of blocks during processing of a current frame.

Abstract: Described herein are systems and methods for locating an object detected in a video. The system detects a bounding box at least partially around an object in a first frame at a first time in the video and a second frame in the video corresponding to a second time. The system determines whether there is no motion within the bounding box of the second frame. The system compares edge information, or color information, or intensity information associated with one or more pixels in the first frame, to edge information, or color information, or intensity information associated with one or more pixels within the bounding box. The system generates a score based on the comparison. The system further determines based on the score if the object is present in the second frame. The system also determines an estimated timeframe window of a first appearance of the object.

Abstract: Methods and systems are provided for automatically generating asset records that are stored and maintained at a database system of a cloud-based computing system. Asset information can be acquired for assets from sources regarding the assets or a representation of the assets. The asset information can be processed to detect assets and analyzed to determine an asset type for each detected asset. For each detected asset, based on an asset type of that detected asset, pertinent header information for that detected asset can be extracted (e.g., asset information and data for that detected asset, associated properties of each detected asset, etc.). An asset record for each detected asset can then be generated, and then stored at the database system, for example, as a row in an asset object of the database system, where each asset record for each detected asset includes pertinent header information for that detected asset.

Abstract: A method for decoding an image by a decoding apparatus comprises the steps of: obtaining merge with motion vector difference (MMVD) flag information of a current block from a bit stream; determining whether or not the current block is a current picture referencing (CPR) coding block; if the current block is a CPR coding block, deriving base motion information; deriving motion information of the current block on the basis of the base motion information; generating prediction samples of the current block on the basis of the motion information; and generating reconstruction samples of the current block on the basis of the prediction samples, wherein the MMVD flag information indicates whether or not motion information is derived when the MMVD is applied to the current block, and the CPR coding block is a block coded by using a current picture including the current block as a reference picture.

Abstract: A video decoding method performed by a video decoding device according to this document comprises the steps of: parsing prediction weighted table syntax from a bitstream; parsing information on the number of reference pictures in a reference picture list from the prediction weighted table syntax; deriving weights for weighted prediction on the basis of the information on the number of reference pictures; deriving prediction samples of a current block by performing weighted prediction for the current block on the basis of the weights; and reconstructing a current picture on the basis of the prediction samples, wherein the prediction weighted table syntax may be parsed from a picture header of the bitstream.

Abstract: A video decoding method performed by a video decoding device according to the present document may comprise the steps of: acquiring image information from a bitstream, the image information including a picture header associated with the current picture including a plurality of slices; parsing, from the picture header, at least one of a first flag indicating whether information necessary for an inter-prediction operation for a decoding process is present in the picture header, or a second flag indicating whether information necessary for an intra-prediction operation for the decoding process is present in the picture header; generating prediction samples by performing at least one of intra-prediction or inter-prediction for the slices in the current picture on the basis of at least one of the first flag or the second flag; and generating reconstructed samples on the basis of the prediction samples.

Abstract: Embodiments described herein provide various examples of real-time visual object tracking. In another aspect, a process for performing a local re-identification of a target object which was earlier detected in a video but later lost when tracking the target object is disclosed. This process begins by receiving a current video frame of the video and a predicted location of the target object. The process then places a current search window in the current video frame centered on or in the vicinity of the predicted location of the target object. Next, the process extracts a feature map from an image patch within the current search window. The process further retrieves a set of stored feature maps computed at a set of previously-determined locations of the target object from a set of previously-processed video frames in the video. The process next computes a set of correlation maps between the feature map and each of the set of stored feature maps.

Abstract: A video decoding method executed by a video decoding apparatus according to the present document comprises the steps of: parsing a flag associated with weighted prediction from a bitstream; on the basis of the flag, parsing a prediction weighted table syntax from the bitstream; and on the basis of the prediction weighted table syntax, executing a weighted prediction on a current block in a current picture to reconstruct the current picture, wherein on the basis of the value of the flag being 1, the prediction weighted table syntax may be parsed from a picture header of the bitstream, and on the basis of the value of the flag being 0, the prediction weighted table syntax may be parsed from a slice header of the bitstream.

Abstract: A video processing method is provided, including: performing a conversion between a coded representation of a video including one or more video regions and the video, wherein the coded representation includes reshaping model information applicable for in-loop reshaping (ILR) of some of the one or more video regions, wherein the reshaping model information provides information for a reconstruction of a video unit of a video region based on a representation in a first domain and a second domain and/or scaling chroma residue of a chroma video unit, wherein the reshaping model information includes a parameter set that includes a first syntax element that derives a number of bits used to represent a second syntax element specifying an absolute delta codeword value from a corresponding bin, and wherein the first syntax element has a value smaller than a threshold.

Abstract: The present disclosure provides methods, apparatus and non-transitory computer readable medium for processing video data. According to certain disclosed embodiments, a method includes: determining a set of parameters from a plurality of sets of parameters wherein the set of parameters includes a scaling factor; determining a predicted sample value of a first chroma component based on the set of the parameters, a reconstructed sample value of a luma component and a reconstructed sample value of a second chroma component; and signaling an index associated with the set of parameters in a bitstream.

Abstract: A multi-camera vehicle vision system and method. In one embodiment a map is generated about a moving vehicle. Frames of image data are provided with a series of cameras extending along a surface of the vehicle. The image data frames are processed to identify an object of interest. An object of interest is classified among a set of object types and location of an identified object of interest is determined. Object type and location information is provided to a control unit spaced apart from the cameras via a data link. Road map data is generated to illustrate changes in position of the moving vehicle along a roadway based on data other than the image data provided by the cameras. A display of the road map data is generated with the object type and location information overlaid on the road map data to indicate object location relative to the vehicle.

Abstract: A Method of decoding an encoded video bitstream using at least one processor includes: obtaining an encoded video bitstream, the encoded video bitstream including encoded color components; entropy parsing the encoded color components; dequantizing the color components and obtaining transform coefficients of the color components; applying a joint components secondary transform (JCST) on the transform coefficients of the color components, thereby generating JCST outputs; performing a backward transform on the JCST outputs, thereby obtaining residual components of the color components; and decoding the encoded video bitstream based on the residual components of the color components.

Abstract: Enhancing edges of objects in a thermal image comprises receiving a thermal image and generating a gradient magnitude image comprising a plurality of pixels having associated gradient magnitude values. The gradient magnitude image is partitioned into subregions and gradient magnitude statistics are calculated for each. Mapping parameters are calculated for each of the subregions that equalize and smooth a dynamic range of the corresponding gradient magnitude statistics across the subregions. The mapping parameters calculated for each of the subregions are applied to pixels in the subregions to generate enhanced gradient magnitude values having equalized luminosity and contrast, and a wireframe image is formed therefrom having enhanced edges of objects. The wireframe image is displayed on a display device, wherein the wireframe image appears as a decluttered line drawing where the enhanced edges have increased luminosity and contrast compared to the thermal image to reduce the cognitive load of the user.

Abstract: Devices, systems and methods for video processing are described. An exemplary method for video processing includes determining, for a block of a video, a quantization parameter associated with the block, coding the block of the video into a bitstream representation of the video as a palette coded block in part based on a modified value of the quantization parameter, and signaling coded information related to the quantization parameter in the bitstream representation.

Abstract: Aspects of the disclosure include methods, apparatuses, and non-transitory computer-readable storage mediums for video encoding/decoding. An apparatus includes processing circuitry that determines directionality information of a restoration filter unit included in a video frame based on at least one of a constrained directional enhancement filter (CDEF) process or an intra prediction mode. The processing circuitry determines one of a plurality of sets of filter parameters of a restoration filter process based on the directionality information of the restoration filter unit. The processing circuitry performs the restoration filter process on the restoration filter unit based on the one of the plurality of sets of filter parameters. The processing circuitry reconstructs the video frame based on the filtered restoration filter unit.

Abstract: An active sensor for performing active measurements of a scene is presented. The active sensor includes at least one transmitter configured to emit light pulses toward at least one target object in the scene, wherein the at least one target object is recognized in an image acquired by a passive sensor; at least one receiver configured to detect light pulses reflected from the at least one target object; a controller configured to control an energy level, a direction, and a timing of each light pulse emitted by the transmitter, wherein the controller is further configured to control at least the direction for detecting each of the reflected light pulses; and a distance measurement circuit configured to measure a distance to each of the at least one target object based on the emitted light pulses and the detected light pulses.

Abstract: Disclosed are a method for decoding a video signal and an apparatus therefor. Specifically, a method for decoding an image based on an inter-prediction mode may include: configuring a merge candidate list by using motion information of a spatial candidate and a temporal candidate adjacent to a current block; parsing a first syntax element indicating a particular candidate applied to inter-prediction of the current block among a predefined number of candidates in the merge candidate list; deriving a refined candidate by adding a motion vector offset to a motion vector of a candidate indicated by the first syntax element; and generating a prediction block of the current block by using the motion information of the refined candidate.