Abstract: A method for calibrating a vehicular vision system includes disposing a camera at a vehicle, disposing a processor at the vehicle, and disposing a video display screen in the vehicle so as to be viewable by the vehicle driver. The video display screen is operable to display video images derived from image data captured by the imager of the camera. Image data is captured by the imager of the camera and provided to the processor. The video display screen displays video images derived from image data captured by the imager of the camera. The processor generates a graphic overlay for display with the video images at the video display screen. Responsive to processing captured image data, the vehicular vision system is calibrated by adapting an orientation and position of the image data relative to the generated graphic overlay to a corrected orientation and position relative to the generated graphic overlay.

Abstract: A document scanner includes an enclosure with a scanning area. A transparent platform in the scanning area allows a user to position a document for authentication. A top camera takes a picture of the top of the document and a bottom camera takes a picture of the bottom under multiple light conditions including UV, IR, and white light. Mirrors reduce the enclosure size and multiple computers within the enclosure share work to process image data and determine document type. Types are searched in order based historically detected types. Barcode data is decoded and image samples are filtered as one of the computers finds a match. Security features are checked for the detected type and fake variants of the detected type are checked. Card information and formatting is validated and face data captured from a face camera and as shown on the document are matched against a database of banned users.

Abstract: An information collection system includes a control device installed at a vehicle, a collection device that collects obstacle information from a plurality of the control devices, and a relay device that relays communications between the control device and the collection device. A first processor of the control device calculates a degree of confidence that an obstacle as included in a captured image captured by an image capture device provided at the vehicle, and transmits image information related to the captured image, position information added to the captured image, and the degree of confidence, to the relay device. A second processor of the relay device receives the image information, the position information, and the degree of confidence, from the control devices, and identifies an obstacle included in a captured image according to the image information in descending order of the degree of confidence.

Abstract: A bridge crane anti-swing method based on first-order dynamic sliding mode variable structure includes steps of: constructing a two-dimensional bridge crane system model and a crane system control model, respectively; performing differentiation on two sliding mode surfaces containing swing angle dynamic change and rope length dynamic change to obtain a crane position dynamic sliding surface s1 and a rope length dynamic sliding mode surface s2, respectively; combining a displacement x, a length l and a swing angle ? in the two-dimensional bridge crane system model with the crane position dynamic sliding surface s1 and rope length dynamic sliding mod surface s2 in the crane system control model to obtain a relationship among a horizontal traction force f1, an along-rope traction force f2, the displacement x, the length l and the swing angle ?.

Abstract: A method for processing an online video stream may include determining a transmission performance of a network for a queue of video frames, wherein each video frame in the queue may be associated with a priority level. The method may also include determining a maximum discarding level based on the transmission performance of the network. The method may further include removing a target video frame of which the associated priority level is lower than or equal to the maximum discarding level from the queue.

Abstract: The techniques described herein relate to methods, apparatus, and computer readable media configured to encode and/or decode video data. A prediction mode is determined for intra prediction coding a current data unit, where the determined prediction mode is a most probable mode of a plurality of most probable modes determined for the current data unit. The MPM information of the determined prediction mode is encoded using a coding bin, including context encoding the bin based on whether the bin is a first coding bin for the MPM information.

Abstract: A fluorescence imaging system is configured to generate a video image onto a display. The system includes a light source for emitting infrared light and white light, an infrared image sensor for capturing infrared image data, and a white light image sensor for capturing white light image data. Data processing hardware performs operations that include filtering the infrared image data with a first digital finite impulse response (FIR) filter configured to produce a magnitude response of zero at a horizontal Nyquist frequency and a vertical Nyquist frequency. The operations also include filtering the infrared image data with a second digital FIR filter configured with a phase response to spatially align the white light image data with the infrared image data. The operations also include combining the white light image data and the infrared image data into combined image data and transmitting the combined image data to the display.

Abstract: An apparatus for generating view images for a scene comprises a store (101) which stores three dimensional scene data representing the scene from a viewing region. The three dimensional scene data may e.g. be images and depth maps captured from capture positions within the viewing region. A movement processor (105) receives motion data, such as head or eye tracking data, for a user and determines an observer viewing position and an observer viewing orientation from the motion data. A change processor (109) determines an orientation change measure for the observer viewing orientation and an adapter (111) is arranged to reduce a distance from the observer viewing position relative to the viewing region in response to the orientation change measure. An image generator (103) generates view images for the observer viewing position and the observer viewing orientation from the scene data.

Abstract: Fluorescence imaging with reduced fixed pattern noise is disclosed. A method includes actuating an emitter to emit a plurality of pulses of electromagnetic radiation and sensing reflected electromagnetic radiation resulting from the plurality of pulses of electromagnetic radiation with a pixel array of an image sensor to generate a plurality of exposure frames. The method includes applying edge enhancement to edges within an exposure frame of the plurality of exposure frames. The method is such that at least a portion of the plurality of pulses of electromagnetic radiation emitted by the emitter comprises one or more of electromagnetic radiation having a wavelength from about 795 nm to about 815 nm.

Abstract: The disclosure relates to an endoscopic system that includes an image sensor, an emitter and an electromagnetic radiation driver. The image sensor includes a pixel array and is configured to generate and read out pixel data for an image based on electromagnetic radiation received by the pixel array. The pixel array includes a plurality of lines for reading out pixel data. The pixel array also has readout period that is the length of time for reading out all the plurality of lines of pixel data in the pixel array. The emitter is configured to emit electromagnetic radiation for illumination of a scene observed by the image sensor. The electromagnetic radiation driver is configured to drive emissions by the emitter. The electromagnetic radiation driver includes a jitter specification that is less than or equal to about 10% to about 25% percent of the readout period of the pixel array of the image sensor.

Abstract: A method and system for encoding a stereoscopic image pair is disclosed. Groups of pixels are analyzed to determine the depth of each pixel group. The number of bits per pixel used to encode each pixel group is selected based on the depth of that pixel group. Therefore, images of objects closer to the camera pair, which appear closer to the viewer, are encoded with a larger number of bits per pixel than objects perceived to be farther from the viewer. The number of bits per pixel may also be increased based on a number of objects depicted or motion detected. The size of prediction blocks used to encode image portions may also be determined based on an angular distance of an image portion relative to the center of the frame. Therefore, smaller prediction blocks may be used to encode image portions closer to the center of the frame.

Abstract: A device for decoding video data includes a memory configured to store the video data; and one or more processors configured to decode syntax information that indicates a selected intra prediction mode for the block of video data from among a plurality of intra prediction modes. The one or more processors apply an N-tap intra interpolation filter to neighboring reconstructed samples of the block of video data according to the selected intra prediction mode, wherein N is greater than 2. The one or more processors reconstruct the block of video data based on the filtered neighboring reconstructed samples according to the selected intra prediction mode.

Abstract: Methods and systems for monitoring an industrial process are disclosed. Some aspects of the system arrange multiple imaging sensors to image machinery associated with an industrial process. Regions of interest within images acquired by the multiple imaging sensors may be monitored for abnormal thermal conditions, and alerts generated as needed. Alerts may also be generated if temperatures within a region of interest exceed thresholds associated with that region of interest. Each region of interest may be independently monitored and have individualized alerting thresholds. In some aspects, images from the multiple imaging sensors may be stitched together, with the regions of interest based on the stitched image. In other aspects, regions of interest within images from separate imaging sensors may be linked together so as to share at least common alerting thresholds.

Abstract: A surveillance system for mobile surveillance access to remote areas comprising a housing sized to be manually portable, and a power supply, an input port, a video converter, an encoder, and a router all within the housing. The power supply is configured to provide power to the system. The input port is configured to receive a video stream from a camera. The video converter is configured to convert the video stream from a digital signal to an analog signal. The encoder is configured to convert the video stream into a reduced bitrate digital stream having a bitrate less than or equal to 3 megabits per second. The router is configured to transmit the reduced bitrate digital stream over at least two of a plurality of communication paths simultaneously. The system is manually portable and configured to livestream the video stream to the internet in real time.

Abstract: A system for providing improved video quality and compression efficiency during encoding by detecting video segments having film grain approaching the “Red Lady” problem. The system detects when film grain approaches the level of the “Red Lady” problem by measuring frame-by-frame temporal differences (ME scores). From the ME scores, two key indicators are identified: (1) The average temporal difference in frames with an intermediate motion level higher than frames of non-noisy video; and (2) The fluctuation of the temporal differences between frames in a group is very small. When these indicators identify a high film video, a signal is provided to an encoder which allocates less bits to I frames and more bits to P and B frames than for other frames of video without comparable film grain.

Abstract: An apparatus for video decoding includes processing circuitry configured to receive a split direction syntax element, a first index syntax element, and a second index syntax element that are associated with a coding block coded with a triangular prediction mode. The coding block can be partitioned into two triangular prediction units according to a split direction indicated by the split direction syntax element. The first and second index syntax elements can indicate a first merge index and a second merge index to a merge candidate list constructed for the two triangular prediction units. The coding block can be reconstructed according to the split direction, the first merge index, and second merge index.

Abstract: A method and apparatus is described comprising: obtaining first input data from a first camera of a multi-camera device; obtaining second input data from a second camera of the multi-camera device (wherein the second camera is orientated in a different direction to the first camera); defining a first region or object of interest for the first camera and/or a second region or object of interest for the second camera; tracking the first region or object of interest and/or the second region or object of interest; generating a first output data based on the first input data; generating a second output data based on the second input data; and generating a multi-camera output that includes the first and second output data.

Abstract: Disclosed is a method of decoding an image and a method of encoding an image. The method of decoding an image includes: obtaining motion-constrained tile set information; determining, on the basis of the motion-constrained tile set information, a first boundary region of a collocated tile set within a reference picture, which corresponds to a motion-constrained tile set; padding a second boundary region corresponding to the first boundary region; and performing inter prediction on the motion-constrained tile set by using a collocated tile set that includes the padded second boundary region.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a storage device, are disclosed. A system includes one or more processors and one or more computer storage media storing instructions that are operable, when executed by the one or more processors, to cause the one or more processors to perform operations. The operations include: obtaining an image from a camera coupled to a garage; determining that a garage door has opened; in response to determining that the garage door has opened, determining that a vehicle position satisfies an alert criteria based on the image from the camera; and in response to determining that the vehicle position satisfies the alert criteria based on the image from the camera, providing a visual alert for a driver of the vehicle on a signaling device coupled to the garage.

Abstract: A system and method for rendering an object box of an object in an image is provided in the present disclosure. The method includes obtaining a plurality of images, in a temporal sequence, each of the plurality of images relating to an object. The method also includes obtaining a first processed image by performing a smart algorithm analysis on a first image in the plurality of images, the smart algorithm analysis including identifying the object in the first image and determining a first coordinate of the object in the first image. The method further includes determining a first pixel distance between the object in two adjacent images in the plurality of images and rendering an object box for the object in each of the plurality of images for display based on the first coordinate of the object in the first image and the first pixel distance.