Abstract: Systems, methods and apparatus for video processing are described. The video processing may include video encoding, video decoding, or video transcoding. One example method of video processing includes performing a conversion between a video including one or more pictures and a bitstream of the video according to a format rule. The format rule specifies that a first syntax element that indicates whether motion vector difference for a particular reference picture list (RPL) is indicated is conditionally included in the bitstream based on (i) whether a second syntax element indicating whether an RPL information is included in a picture header and/or (ii) a number of reference pictures in the particular RPL in case that the RPL information is present in the picture header.

Abstract: A control device for a microscope includes an actuator configured to shift a microscopic field of view relative to a sample, and an operating device configured to be operated by a user to control the actuator in accordance with a response characteristic determining a shift sensitivity. The field of view is shifted relative to the sample in response to a user operation of the operating device. The control device further includes a processor configured to determine a total visual magnification, and to control the response characteristic of the operating device based on the total visual magnification. The field of view is visualized by the microscope to the user based on the total visual magnification.

Abstract: A method for visual media processing, including: computing, during a conversion between a current video block of visual media data and a bitstream representation of the current video block, a cross-component linear model (CCLM) and/or a chroma residual scaling (CRS) factor for the current video block based, at least in part, on neighboring samples of a corresponding luma block which covers a top-left sample of a collocated luma block associated with the current video block, wherein one or more characteristics of the current video block are used for identifying the corresponding luma block.

Abstract: An image processing device includes an image encoder, a memory and an image decoder. The image encoder receives an input image frame, retrieves luminance information and chrominance information from the input image frame, respectively, encodes the luminance information to generate an encoded luminance frame, and encodes the chrominance information to generate an encoded chrominance frame. The memory includes a first memory portion, a second memory portion and a third memory portion. The first memory portion stores the encoded luminance frame, and the second memory portion or the third memory portion stores the encoded chrominance frame. The image decoder reads the encoded luminance frame from the first memory portion to perform decoding, and reads the encoded chrominance frame from the second memory portion or the third memory portion for decoding.

Abstract: Methods, systems and devices for coding the picture order count in video bitstream processing. An example method of video processing includes performing a conversion between a video comprising one or more pictures and a bitstream of the video, wherein the bitstream conforms to a format rule, wherein the format rule specifies that a derivation of a picture associated with a first flag and in a decoding process for a picture order count is based on a second flag, wherein the picture associated with the first flag is a previous picture in a decoding order that has (i) a first identifier that is the same as a slice or picture header referring to a reference picture list syntax structure, (ii) a second identifier and the second flag being equal to zero, and (iii) a picture type different from a random access skipped leading picture and a random access decodable leading picture.

Abstract: A decoding device and a method of decoding implemented by a video decoder are disclosed. The decoding method includes receiving a coded video bitstream, where the coded video bitstream contains a gradual decoding refresh (GDR) picture and a first flag having a value; setting a value of a second flag equal to the value of the first flag, where the value of the second flag derived for the video decoder under test is applied for a hypothetical reference decoder (HRD); and when the value of the second flag is equal to one, emptying all picture storage buffers in a decoded picture buffer (DPB) without output of pictures contained in the DPB and setting a DPB fullness parameter to zero.

Abstract: A digital holographic microscope that includes a light source and a photonic integrated circuit. The photonic integrated circuit can include a branching waveguide optically coupled to the light source, and a multi-angle illumination device optically coupled to the branching waveguide. In various examples, the multi-angle illumination device includes an optical phased array that includes a plurality of light emitters. In various examples, the multi-angle illumination device includes a grating coupler.

Abstract: Disclosed is a video signal processing method and device for encoding or decoding a video signal.

Abstract: An information processing apparatus includes one or more memories storing instructions, and one or more processors executing the instructions to acquire a captured image and a distance image, detect an object from the captured image, acquire first distance information indicating a distance to the detected object, acquire a grounding position of the detected object based on the captured image and acquire second distance information indicating a distance to the detected object based on the first distance information and the acquired grounding position.

Abstract: An encoding method, a decoding method, an encoder, a decoder, and a storage medium are provided. The encoding method comprises: determining input feature map data (S201); performing relevant processing on the input feature map data to obtain a plurality of feature sub-maps (S202); reordering the plurality of feature sub-maps to obtain a quasi time domain sequence and corresponding reordering information (S203); and encoding the quasi time domain sequence and the reordering information to generate a bitstream (204).

Abstract: A 3D measuring instrument and method of operation is provided that includes a registration camera and a an autofocus camera. The method includes capturing with the registration camera a first registration image of a first plurality of points and a first image with the first camera with the instrument in a first pose. A plurality of three-dimensional (3D) coordinates of points are determined based on the first image. A second registration image of a second plurality of points is captured in a second pose and a focal length of the autofocus camera is adjusted. A second surface image is captured with the first camera having the adjusted focal length. A compensation parameter is determined based in part on the captured second surface image. The determined compensation parameter is stored.

Abstract: Disclosed are a super-resolution microscopic imaging method and apparatus, a computer device, and a storage medium. The method includes the following steps: collecting a fluorescent signal sequence of a set of samples to be observed; determining the number of iterations of deconvolution; performing an iteration of pre-deconvolution on each frame of an initial image in the fluorescent signal sequence before outputting when the iteration reaches half of the number of iterations; performing two reconstructions on the output image; and performing a second iteration of deconvolution on the image after the two reconstructions before outputting when the iteration reaches the number of iterations or half of the number of iterations.

Abstract: Innovations in adaptive encoding and decoding for units of a video sequence can improve coding efficiency. For example, some of the innovations relate to encoding/decoding that includes adaptive switching of color spaces between units within a video sequence. Other innovations relate encoding/decoding that includes adaptive switching of color sampling rates between units within a video sequence. Still other innovations relate encoding/decoding that includes adaptive switching of bit depths between units within a video sequence.

Abstract: There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform parsing at least one video parameter set comprising at least one syntax element indicating whether at least one layer in the scalable bitstream is one of a dependent layer of the scalable bitstream and an independent layer of the scalable bitstream, coding a picture in the dependent layer by parsing and interpreting an inter-layer reference picture list, and coding a picture in an independent layer without parsing and interpreting the inter-layer reference picture list.

Abstract: A vehicle includes a window having a display. The display includes a substrate, a light source disposed at a first location of the substrate, a light sensor disposed at a second location of the substrate, and a first optical medium disposed on the substrate over the light source. The first optical medium includes a surface at an angle that prevents light from the light source from passing through the first optical medium and into the light sensor.

Abstract: Techniques are presented for the detection and management of collision warning (CW) events. A training dataset comprising videos of vehicle collisions and non-collisions, sensor readings, environmental conditions, and more is utilized to train a CW classification model for detecting potential collision events in vehicles. A backend CW classification model, with greater computational resources, employs a more complex neural network to review CW events received by the Behavioral Monitoring System (BMS) based on video data, achieving higher precision and reducing false positives. The CW model is installed in vehicles for real-time detection, while the backend model is deployed at the BMS. The BMS validates detected CW events, filters out false positives, and streamlines the review process for fleet administrators and customers. Additional BMS filtering operations include assessing non-proximity-related CW events and camera impairments, with the filtered CW events presented for review in the safety inbox.

Abstract: A technique for performing video operations is provided. The technique includes characterizing a frame as a flash frame; setting the flash frame as a non-intra frame; prohibiting encoding of frames other than the flash frame with reference to the flash frame; and applying a positive quantization parameter (“QP”) offset to the flash frame.

Abstract: A decoder includes circuitry and memory. In both of a first type of residual decoding where an inverse orthogonal transform is applied and a second type of residual decoding where the inverse orthogonal transform is skipped, wherein when a restriction on a number of CABAC processes allows CABAC decoding of a set of coefficient information flags, the circuitry: decodes the coefficient information flags by CABAC; and otherwise, the circuitry: skips the CABAC decoding of the coefficient information flags; and the circuitry decodes a remainder value of the coefficient with Golomb-Rice decoding when the coefficient information flags are decoded; and otherwise the circuitry decodes a value of the coefficient with the Golomb-Rice decoding, wherein in the second type of residual decoding, the circuitry decodes absolute value flags each relating to an absolute value of the coefficient after decoding the coefficient information flags and before decoding the remainder value of the coefficient.

Abstract: For a coding block of an image, a luma prediction block is generated, a luma residual block is generated, a quantized luma block is generated after transforming the luma residual block using a luma transform type, and the quantized luma block is entropy encoded. A chroma prediction block is generated, a chroma residual block is generated, an initial chroma transform type for the chroma residual block is determined as the luma transform type, a quantized chroma block is generated using the chroma residual block transformed by a final chroma transform type, and the quantized chroma block is entropy encoded. When the initial chroma transform type is other than a default transform type, the final chroma transform type is the initial chroma transform type or the default transform type, and quantized coefficients of the quantized chroma block depend upon quantized coefficients of the quantized luma block.

Abstract: A system and method for real-time monitoring of personal protective equipment (PPE) compliance at a worksite. The system includes a processor, a host memory, a graphical processing unit (GPU), a GPU memory, a storage device, an input device, a plurality of cameras, and a display device. The system creates multiple inference engines and loads input frames from the storage device for pre-processing. The pre-processed frames are processed to obtain annotations and generate an output file. The system also includes a preparatory area and an operations area with cameras configured to capture and transmit video frames. The system can process input frames at a rate of at least 15 frames per second, providing real-time PPE compliance information.