Abstract: Provided is in-loop filtering technology using a trained deep neural network (DNN) filter model. An image decoding method according to an embodiment includes receiving a bitstream of an encoded image, generating reconstructed data by reconstructing the encoded image, obtaining information about a content type of the encoded image from the bitstream, determining a deep neural network (DNN) filter model trained to perform in-loop filtering by using at least one computer, based on the information about the content type, and performing the in-loop filtering by applying the reconstructed data to the determined DNN filter model.

Abstract: A pipe inspection system including a camera head, a push-cable, and a controller platform for use in inspecting pipes or other cavities is disclosed.

Abstract: An imaging apparatus includes: an imager configured to generate an imaging signal; a transmission channel configured to connect a controller and the images; a superimposed signal generator that is arranged on a proximal end side of the transmission channel, the superimposed signal generator being configured to generate a superimposed signal by superimposing a pulsed data signal and a pulsed reference clock signal, and output the generated superimposed signal to the transmission channel; a first extractor that is arranged on a distal end side of the transmission channel, the first extractor being configured to extract the data signal and the reference clock signal from the generated superimposed signal; and a second extractor that is arranged on the distal end side of the transmission channel, the second extractor being configured to extract the negative voltage from the generated superimposed signal.

Abstract: An observation device includes: an illumination unit that generates illumination light to be radiated onto cells floating in a culture fluid inside a culture vessel; a light receiving unit that receives observation light coming from the cells that have been irradiated with the illumination light, the observation light being imaged by an image-forming optical system; and a casing that has a transmissive section so as to transmit the illumination light and the observation light and that accommodates the illumination unit and the light receiving unit, wherein the casing has an elongated cylindrical form that is configured to be inserted into the culture fluid via a port used to insert a tube into the culture vessel.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes processing circuitry that decodes prediction information for a current block in a current coded picture that is part of a coded video sequence. The prediction information indicates a fractional motion vector for the current block. The processing circuitry determines whether one of a block width and a block height of the current block is below a first threshold. The processing circuitry selects one of an integer motion vector, a first interpolation filter, and a second interpolation filter for the current block when the one of the block width and the block height of the current block is determined to be below the first threshold. The processing circuitry reconstructs the current block based on the selected one of the integer motion vector, the first interpolation filter, and the second interpolation filter.

Abstract: A system for detecting the presence of pests, the system comprising: at least one remote camera system, each of the at least one remote camera system comprising an image capture device coupled to a processor and a wireless transmitter, each of the at least one remote camera system having a pest detection surface and being configured to: capture one or more image of the pest detection surface; process the captured one or more image to recognise the potential presence of a target pest on the pest detection surface; and transmit data from the captured one or more image in response to recognising the potential presence of one or more target pests; and a server configured to: receive the transmitted data; process the transmitted data to verify the potential presence of the target pest on the pest detection surface; and provide an output indicating the verification.

Abstract: A reinforcement learning method for frame-level bit allocation is disclosed. The reinforcement learning method includes steps of: (a) at a testing time, computing a state according to a plurality of features; (b) determining an action according to a policy; (c) determining a number of bits allocated to an i-th frame in a group of pictures (GOP) according to the action, a GOP-level bit budget and the state, wherein i is a positive integer; (d) encoding the i-th frame according to the number of bits allocated to the i-th frame in the GOP; and (e) repeating the steps (a)˜(d) until an end of the GOP.

Abstract: A method comprising: encoding an input picture into a coded constituent picture (1200); reconstructing, as a part of said encoding, a decoded constituent picture corresponding to the coded constituent picture (1202); encoding a spatial region into a coded tile (1204), the encoding comprising: determining a horizontal offset and a vertical offset indicative of a region-wise anchor position of the spatial region within the decoded constituent picture (1204a); encoding the horizontal offset and the vertical offset (1204b); determining that a prediction unit at position of a first horizontal coordinate and a first vertical coordinate of the coded tile is predicted relative to the region-wise anchor position, wherein the first horizontal coordinate and the first vertical coordinate are horizontal and vertical coordinates, respectively, within the spatial region (1204c); indicating that the prediction unit is predicted relative to a prediction-unit anchor position that is relative to the horizontal and vertical off

Abstract: An inspection system and method with a variable-diameter traveling robot for inspection of a natural gas pipeline. The inspection system includes a pipeline inspection robot, a cable reel, a hydraulic pump and an information acquisition control terminal. The pipeline inspection robot includes an electronic cabin and a traveling mechanism. The electronic cabin includes a first digital camera, a second digital camera, a first digital camera mounting plate, a second digital camera mounting plate, a drum, a printed circuit board, a magnetic flux leakage probe, and a backup battery. The traveling mechanism includes a first traveling part, a second traveling part, an inner ratchet, an inner ratchet base, a slider, a long shaft, a hydraulic cylinder, and a hydraulic pipe. The cable reel includes a power line, a conversion module, and a communication line. The information acquisition control terminal is a mobile terminal having an analysis module and a control module.

Abstract: A method and system for video system using coding modes including an Inter prediction mode and an Intra Block Copy (IntraBC) mode are disclosed. A syntax element in a bitstream is determined to indicate whether two versions of a reconstructed current image unit are needed. If two versions of the reconstructed current image unit are needed, a loop-filtered version of the reconstructed current image unit and a non-loop-filter version of the reconstructed current image unit are allowed to be stored and used as reference data. Otherwise, only one version of the reconstructed current image unit is stored as the reference data. According to another method, bi-prediction mode is converted to uni-prediction mode for a certain prediction mode, where the bandwidth exceeds the existing worst case.

Abstract: A whole slide image creation device including a first image-capture control unit for capturing an image-capture region for a pathological specimen at a first magnification and a second magnification; a storage unit for storing a first training image corresponding to the first magnification and a second training image corresponding to the second magnification; a calculation unit for pattern matching between a first image captured at the first magnification and the first training image to calculate a first degree-of-match, and between a second image captured at the second magnification and the second training image to calculate a second degree-of-match; a magnification selection unit for selecting the first magnification or the second magnification for capturing the entire pathological specimen on the basis of the first degree-of-match and the second degree-of-match; and a second image-capture control unit for capturing the entire pathological specimen at the selected magnification for each segmented region.

Abstract: Various techniques related to a sensor for use with autonomous driving and/or navigation of a vehicle. The techniques can include use of an elongated threaded member, an intermediate threaded member, and a tertiary member. The members can be operable to extend or retract a vehicle sensor on a platform. The members can also enable the sensor to retract upon application of a force external to the vehicle.

Abstract: A system for the automatic grading of a cut/polished gemstone (SUT) includes an enclosure with a stage for mounting the cut/polished SUT. The enclosure further includes one or more sources of broadband visible (BBV) light, the sources of BBV light being controllable by a programmable controller; an image sensor for capturing a plurality of images of a mounted SUT, and one or more sources of UV light mounted within the enclosure. The controller captures images of the mounted SUT from one or more selected angles relative to the sensor elevation axis and relative to the position of the SUT on the stage rotation axis; an image capturing module is configured for processing the one or more images; and, a light grade calculation module is configured for grading the cut/polished SUT using light indicative parameters from at least a part of the one or more images captured.

Abstract: A method and apparatus for deriving a sub-block motion vector for the current sub-block based on a motion-model function depending on the current sub-block location are disclosed. The derived sub-block motion vector is then used for encoding or decoding the sub-block. The motion-model function may correspond to an affine motion-model function or a bilinear motion-model function. In one embodiment, a new Merge mode can be used to apply prediction of a current block by applying prediction on the sub-block basis using the sub-block motion vector derived from the motion-model function. In another embodiment, an additional inter prediction mode can be used to apply prediction of a current block by applying prediction on the sub-block basis using the sub-block motion vector derived from the motion-model function.

Abstract: Aspects of the subject disclosure may include, for example, obtaining data indicative, for a frame of a video, of a field of view of a user; determining from a set of homogeneous tiles of the frame a subset of the homogeneous tiles that covers the field of view, wherein the set of homogeneous tiles has been constructed prior to the obtaining of the data; and merging at least a first tile of the set of homogeneous tiles and a second tile of the set of homogenous tiles into a larger tile, wherein the merging is based upon at least one parameter. Other embodiments are disclosed.

Abstract: A machine-vision system for monitoring a quality metric for a product. The system includes a controller configured to receive a digital image from an image acquisition device. The controller is also configured to analyze the digital image using a first machine-vision algorithm to compute a measurement of the product. The system also includes a vision server connected to the controller, and configured to compute a quality metric and store the digital image and the measurement in a database storage. The system also includes a remote terminal connected to the vision server, and configured to display the digital image and the quality metric on the remote terminal.

Abstract: A self-adjusting LED warning light control system includes an image capturing device, an image processing device, a car distance detection device, a warning light control device, and an LED warning light. The LED warning light includes a red LED component, a middle partition, and a blue LED component. The image capturing device is provided for collecting image data for the front of the police car to obtain a front image; the image processing device is provided for performing an image processing of the front image; the car distance detection device is provided for confirming the front vehicle distance according to an output of the image processing device; the warning light control device is provided for confirming a control strategy of the LED warning light according to the output of the car distance detection device. This disclosure can achieve a self-adjusting control of the LED warning light.

Abstract: A doorbell system (1) includes a plurality of doorbells (2-1 to 2-n) each of which is attached to each residence and includes an operation unit (22) and a camera (26), and a control unit (4) capable of performing communication with the plurality of doorbells (2-1 to 2-n). The control unit (4) is configured to acquire position information of each of the plurality of doorbells (2-1 to 2-n) and an image captured by the camera (26), to generate target information about a target, based on the position information and the image, and to transmit the target information to an external device (3-1 to 30n) associated with a specific user.

Abstract: The present technique relates to an image processing apparatus and method that allow to suppress an increase in processing time. The image processing apparatus includes an information control unit that obtains information required for image processing for a focused pixel, using only information belonging to a slice including the focused pixel, the focused pixel being a processing target, and the information being obtained using reference information belonging to a different pixel than the focused pixel; and an image processing unit that performs the image processing using the information obtained by the information control unit. The present disclosure can be applied to image processing apparatuses.

Abstract: A video system for video surveillance or video monitoring includes a video source, a video control system, and a video management system. The video management system is configured to receive configuration data and generate maps based on the configuration data, wherein at least one of the maps is associated with the video source. The video management system displays the map associated with the video source and displays a graphical symbol on the map which indicates the location of the video source. The video management system then receives a selection of the video source, receives information associated with the selected video source, and displays the received information.