Abstract: Methods and systems for adaptive chroma reshaping are discussed. Given an input image, a luma-reshaped image is first generated based on its luma component. For each chroma component of the input image, the range of the pixel values in the luma reshaped image is divided into bins, and for each bin a maximal scale factor is generated based on the chroma pixel values in the input image corresponding to the pixels of the luma reshaped image in the bin. A forward reshaping function is generated based on a reference reshaped function and the maximal scale factors, and reshaped chroma pixel values for the chroma component are generated based on the forward reshaping function and the corresponding pixel values in the luma reshaped image. Implementations options using look-up tables for mobile platforms with limited computational resources are also described.

Abstract: An image sensor includes a plurality of optical filters, a plurality of transmissive members, an imaging section, and a signal processing section. The optical filters transmit visible rays having a wavelength enabling visual recognition of a primary color, and the transmissive members transmit infrared rays. A plurality of imaging elements of the imaging section are constituted by a plurality of groups. Each of the imaging elements includes optical filters or transmissive members. The signal processing section determines the luminance of each pixel of a produced image, based on measurement values measured by the imaging elements of a group corresponding to the pixel. At least one imaging element of each group is provided with a transmissive member, and the remaining one or more imaging elements are provided with the optical filters having no color or a primary color allocated to the group.

Abstract: An automated door-opening device is disclosed that includes a first sensor disposed on the outside of the door. The first sensor is adapted to recognize a predetermined pattern of a gesture made by a patron. The gesture made in front of the first sensor opens the door by a first actuator. A second actuator can be used to lock or unlock the door, thereby providing full hand-free operation of the door. A hinge system is disclosed that includes three off-set hinges adapted to utilize the weight of the door to cause the door to self position and allow manual operation of the door.

Abstract: Validation of asset movement can begin with the definition of a virtual tripwire for video cameras of a video surveillance system that monitor a defined area of interest through which RFID-identified assets are conveyed. The virtual tripwire can visually define a boundary within the view field of the video camera. The video camera can detect the movement of an asset through a virtual tripwire and an asset management system can be notified of the potential misdirection of the asset. The asset management system can obtain the asset's RFID data from a RFID handling system that monitors the area of interest. The validity of the detected movement can be determined using RFID data and an asset movement specification that defines pathing rules for assets and virtual tripwires. When the movement of the asset is determined to be invalid, a record of suspect movement data can be generated for the asset.

Abstract: Herein is disclosed an unmanned aerial vehicle navigation system including one or more cameras configured to detect user image data; and one or more processors configured to determine from the user image data a user eye orientation; select according to a selection criterion a navigation behavior based on the user eye orientation; and determine a navigation instruction to cause the unmanned aerial vehicle to travel in accordance with the navigation behavior.

Abstract: A method, computer readable medium, and system are disclosed for action video generation. The method includes the steps of generating, by a recurrent neural network, a sequence of motion vectors from a first set of random variables and receiving, by a generator neural network, the sequence of motion vectors and a content vector sample. The sequence of motion vectors and the content vector sample are sampled by the generator neural network to produce a video clip.

Abstract: A monitoring system includes an imaging device, a recording device and a monitoring device. The imaging device is configured to image a monitoring target. The recording device is configured to stores image data captured by the imaging device. The monitoring device is configured to generate a composite image data by combining the image data captured by the imaging device and an image data, having the same view angle as that of the captured image data, read out from the recording device and to generate an edge cutout rectangle image data by connecting luminance change points exceeding a predetermined threshold value, starting from a predetermined point in the composite image data.

Abstract: An along track imaging device. The device includes: a plurality of optical sensors positioned in parallel with each other and perpendicular to a direction of travel of the imaging device or an object for continuously capturing a plurality of images from the object, wherein each of the plurality of optical sensors includes a flat optic lens with a narrow angle of view; an imaging sensor coupled to the plurality of optical sensors for sensing the plurality of captured images and generating a plurality of overlaid images; a processor coupled to the imaging sensor for compositing the plurality of overlaid images into a single composite image; a digital storage medium for storing a plurality of composite images in series as a contiguous along track image; and a display device for displaying the contiguous along track image.

Abstract: The present invention relates to a method for modifying at least one video frame of a digital video stream to be displayed on a display area. Each correction scheme has one or more specific digital filters based on visual defects perceived by a person with respect to a video frame portion, is configured when predetermined conditions are met and reconfigured whenever the origin position of an eye reference system associated with a respective eye is different from the position of the same origin in said predetermined conditions and/or the orientation of said eye reference system is different from the orientation of the same eye reference system in said predetermined conditions.

Abstract: A method for signaling reference pictures of a picture sequence encoded in a bitstream, the method comprising classifying pictures of the picture sequence into reference pictures and non-reference pictures; providing each reference picture with a unique picture identifier; determining, at least for inter-coded pictures of the picture sequence, all unique combinations of the picture identifier and at least one reference picture identifier, where the at least one reference picture identifier for a particular picture identifies all pictures that may be used as a reference for predicting said particular picture; and assigning intra-coded reference pictures at least with their unique picture identifier and the inter-coded pictures with their corresponding unique combination of the picture identifier and the at least one reference picture identifier.

Abstract: A method and system for de-identifying a video sequence are provided. The method may include the steps of capturing a video sequence, comprising a number of individual frames, including one or more users performing one or more actions, and using activity recognition to recognize one of the one or more actions. One or more of the plurality of frames may be defined as comprising the recognized one or more actions, and a portion of the one or more of the plurality of frames may be identified to remain visible. The non-identified portions of the one or more of the plurality of frames and the non-defined frames may be de-identified. This method may be applied to the determination of whether a user has ingested a medication pill.

Abstract: A video prediction encoding device provided with a picture storage unit storing, as reference pictures to be used for encoding of a subsequent picture, one or more of reconstructed pictures restored from compressed picture data and a memory control unit to control a frame memory in the picture storage unit. When a frame size of input pictures is not more than 1/(2{circumflex over (?)}L) (where L is an integer of one or more) of a maximum frame size of pictures, the memory control unit determines that (2{circumflex over (?)}L) times the maximum number of reconstructed pictures are storable in the frame memory.

Abstract: A system for decoding a video bitstream includes receiving a frame of the video that includes at least one slice and at least one tile and where each of the at least one slice and the at least one tile are not all aligned with one another.

Abstract: When an intra prediction parameter indicates a horizontal prediction process, an intra prediction unit adds a value proportional to a change in a horizontal direction of the luminance values of pixels adjacent to the top of each block, which is a unit for prediction process of a coding block, to the luminance value of a pixel adjacent to the left of the block to set a result of the addition as a predicted value of a prediction image, whereas when the intra prediction parameter indicates a vertical prediction process, the intra prediction unit adds a value proportional to a change in a vertical direction of the luminance values of pixels adjacent to the left of the block to the luminance value of the pixel adjacent to the top of the block to set the result of the addition as a predicted value of the prediction image.

Abstract: Systems and methods are provided for alleviating bandwidth limitations of video transmission and enhancing the quality of videos at a receiver. In particular, an improved video transmission system is provided for generating high-resolution videos. The systems have therein a transmitter and a receiver; the transmitter includes an outer encoder and a core encoder, while the receiver includes a core decoder and an outer decoder. The outer encoder is adapted to receive the video from a source and separately output a salient video and an encoded background, and the outer decoder is adapted to merge the background with the salient video thereby producing an enhanced video. Also provided is a system that simulates pan-tilt-zoom (PTZ) operations without PTZ hardware. Further provided are methods for video transmission whereby a background model is initialized, a background independently encoded, updated incrementally, and the background and the updates transmitted independently from the video.

Abstract: An inspection target is illuminated by an illumination optical unit using a light source. Optical image data of a pattern disposed in the inspection target is acquired by an imaging unit by causing light transmitted or reflected to be incident to a first and second area of a sensor. Reference image data is generated, corresponding to the optical image data, from design data of the pattern. The optical image data is corrected by obtaining a fluctuation of a gradation value of optical image data acquired using light incident to the second area, and correcting a gradation value of optical image data acquired using the light incident to the first area. A line width of the pattern of the corrected data, and a line width error which is a difference between the line widths of corrected data and reference image data are obtained by the line width error obtaining unit.

Abstract: Provided is an image encoding/decoding apparatus and method. The image encoding apparatus may include a motion vector prediction unit to perform a prediction with respect to an arbitrary motion vector of a current block within an image, using at least one of vector information of a motion vector corresponding to an adjacent block and vector information of a previous motion vector of the current block, and a differential determination unit to determine differential information of a motion vector of the current block based on the motion vector predicted in the motion vector prediction unit and an actual motion vector of the current block.

Abstract: The present embodiments introduce a new type of random access point in video bitstreams that can be used for random access operations but can be represented in encoded form at a lower bit-cost as compared to IRAP pictures. The random access point is a dependent random access point (DRAP) picture that is encoded and decoded using an IRAP picture and/or a previous, according to a decoding order, DRAP picture as sole reference picture(s) for the DRAP picture. The DRAP picture is encoded as a trailing picture that may be used for reference and constitutes a random access point in a video bitstream.

Abstract: A vehicle inspection or measurement method and system configured to utilize non-contact optical sensors to acquire images and measurement data associated with at least one vehicle wheel assembly as a vehicle moves through a field of view, and to evaluate the acquired image and/or measurement data to determine at least one dimension associated with an observed feature of the vehicle wheel assembly.

Abstract: A picture with multiple slices is encoded by generating a coded slice representation for each of the slices. A slice flag is set to a first value for the first slice in the picture and corresponding slice flags of the remaining slices are set to a second defined value. A respective slice address is generated for each remaining slice to enable identification of the slice start position within the picture for the slice. A coded picture representation of the picture comprises the coded slice representations, the slice addresses and the slice flags. The slice flags enable differentiation between slices for which slice addresses are required and the slice per picture for which no slice address is needed to identify its slice start position.