Abstract: A ground based wind turbine blade inspection system and method consists of a thermal imaging camera configured to detect propagating defects by acquiring thermal imaging data from a wind turbine blade when it is substantially at thermal equilibrium with respect to surrounding air and analyzing the thermal imaging data with a processor to identify thermal effects associated with latent defects caused by internal friction due to cyclic gravitational stresses and wind loads during normal turbine operation. The system permits latent defects to be identified using a ground-based in situ inspection before they become visually apparent, which allows repairs to be made economically while the blade is in place.

Abstract: Techniques are described for optimizing memory used by a video decoder. A residual coefficient matrix including non-zero value residual coefficients of a larger parent matrix with both non-zero and zero value residual coefficients can be provided to the decoder. Residual coefficient matrix metadata can also be provided so that a modified and reduced inverse transform matrix can be selected and applied to the residual coefficient matrix.

Abstract: An imaging architecture is described for a depth camera mode with mode switching. In one example, an imaging device has a primary camera to capture an image of a scene, a secondary camera to capture an image of the same scene, a third camera to capture an image of a second scene, a processor having a first port coupled to the primary camera to receive images from the primary camera and a second port to receive images, and a multiplexer coupled to the secondary camera and to the third camera to receive the captured images and to alternately couple the secondary camera or the third camera to the second port of the processor.

Abstract: A method for distance calibration of machine vision optical targets and associated observing imaging sensors using separation distances between discrete surface measurement points. First, a spatial position for each surface point is established from a series of observations by the associated observing imaging sensor of the optical targets mounted to a calibration fixture. Second, measures of a linear separation distance between particular pairs of surface points are identified independently from the machine vision observations. All resulting spatial positions and measurements are conveyed to a processing system configured with a set of software instructions for carrying out distance calibration calculations to establish a set of refined distance calibration parameters associated with each combination of optical target and observing imaging sensor. During subsequent use of the machine vision vehicle service system, the parameters are retrieved and utilized to improve vehicle measurement precision.

Abstract: A welding facility inspecting apparatus may include a base apparatus that has a space in the interior thereof and surrounds the space in a horizontal direction, a first extension apparatus, a second extension apparatus, a first camera that is attached to the base apparatus, a second camera that is attached to the base apparatus at a same height as the first camera, a third camera that is attached to the first extension apparatus, a fourth camera that is attached to the second extension apparatus, and a measuring apparatus that is attached to the base apparatus in such a way that the measuring apparatus is disposed in the inner space of the base apparatus and that is configured to measure welding force and welding current of a welding gun.

Abstract: Some demonstrative embodiments include devices, systems and/or methods of orientation estimation of a mobile device. For example, a mobile device may include an orientation estimator to detect a pattern in at least one image captured by the mobile device, and based on one or more geometric elements of the detected pattern, to determine one or more orientation parameters related to an orientation of the mobile device.

Abstract: The invention relates to a method for the synchronization of a set of 3D devices suitable for the processing of data representative of at least one stereoscopic image comprising a first image and a second image.

Abstract: Near-field spray characteristics are established from local measurements which are acquired by data acquisition sub-system capable of complete scanning of the area (volume) of interest in the spray which uses different laser-based probes (shadowgraphy, PIV, diffraction) to obtain drops related measurements. A mechanical patternator measures volume flux distribution of the spray under study. The measurement data are post-processed to obtain spatially-resolved spray characteristics which are mapped in a spherical coordinate system consistent with the kinematics of the spray. A data compression scheme is used to generate compact analytical functions describing the nozzle spray based on the measurement data. These analytical functions may be useful for initiating the nozzle spray in computational fluid dynamics (CFD) based spray dispersion and fire suppression modeling.

Abstract: A remote monitoring system includes: a display unit on which a CG video generated from a three-dimensional CG model is displayed; an input unit which accepts a user's input to the CG video; a three-dimensional CG image generation unit which displays, on the display unit, the CG video after being moved on the basis of the input; an optimal camera calculation unit which specifies a surveillance camera that can pick up a real video similar to the CG video after being moved; and a control unit which controls the surveillance camera that is specified, wherein a real video from the surveillance camera that is controlled is displayed on the display unit.

Abstract: A low-level region detection unit is configured to detect a low-level region from a far-infrared camera image. A transparent region detection unit is configured to detect a low-level region based on at least the near-infrared camera image, the low-level region having a predetermined level or less resulting from being a transparent region that is a region covered with a visually transparent material, within the low-level region detected by the low-level region detection unit. The image segmentation unit is configured to segment a portion of the transparent region from the near-infrared camera image. The superimposition unit is configured to superimpose the portion of the transparent region onto a position of the far-infrared camera image, which corresponds to a position of the transparent region, and generate a synthetic image.

Abstract: The present disclosure discloses a method for evaluating crosstalk in a naked-eye stereoscopic display, including: controlling a display panel to display sequentially viewpoint images; when displaying each of the viewpoint images, each of sub-pixels for displaying a current viewpoint image displays a white image, each of sub-pixels for displaying other viewpoint images displays a black image; obtaining sequentially, on a light emitting side of the display panel, first luminance values of light at respective test angles corresponding to the current viewpoint image; controlling the display panel to display an all-black image, obtaining sequentially second luminance values of light at the respective test angles; determining a crosstalk value of light at one test angle corresponding to any one of luminance peaks in the first luminance values, according to the one of luminance peaks and one second luminance value at the same test angle corresponding to the one of the luminance peaks.

Abstract: An on-board device, that outputs a control signal to a cleaning control unit that controls accumulation removing units used to remove accumulations settled on a photographic lens in an on-board camera by adopting a plurality of methods, includes: an accumulation detection unit that detects an accumulation settled on the photographic lens from a photographic image output from the on-board camera when a vehicle speed input thereto is equal to or higher than a predetermined vehicle speed; a selection unit that selects an accumulation removing unit adopting a first method among the accumulation removing units adopting the plurality of methods; and a removal decision unit that makes a decision, based upon the photographic image, as to whether or not the accumulation has been removed from the photographic lens through a removal operation performed by the accumulation removing unit adopting the first method, which has been selected by the selection unit, wherein: if the removal decision unit decides that the accumul

Abstract: A portable three-dimensional scanner includes at least two image sensing units and a depth map generation unit. When the portable three-dimensional scanner is moved around an object, a first image sensing unit and a second image sensing unit of the at least two image sensing units capture a plurality of first images comprising the object and a plurality of second images comprising the object, respectively. When the first image sensing unit captures each first image of the plurality of first images, a corresponding distance exists between the portable three-dimensional scanner and the object. The depth map generation unit generates a corresponding depth map according to the each first image and a corresponding second image. A plurality of depth maps generated by the depth map generation unit, the plurality of first images, and the plurality of second images are used for generating a color three-dimensional scan result corresponding to the object.

Abstract: Technologies are generally described for automatically optimizing an efficiency of camera placement, numbers, and resolution in multi-camera monitoring and surveillance applications. In some examples, a fraction of a total area may be monitored at a higher resolution than the rest. Employing techniques such as combinatorial state Viterbi technique or combinatorial state trellis technique, a minimum number of cameras that provide the coverage at the needed resolution may be selected. Similarly, a number of points may be covered with at least a predefined number of cameras. For example, a subject of interest may be tracked in a public area, where specific camera(s) may be used to image the subject's face at a higher resolution than the background.

Abstract: A server transmits a probe packet to a terminal, estimates a bandwidth of the network based on information returned from the terminal, calculates a rate used for performing compression coding of screen information and/or an accompanying audio signal, generated by an application on a virtual terminal on the server, so as not to exceed the estimated bandwidth, encodes the screen information and/or the accompanying audio signal at the calculated rate, stores the encoding result in a packet of a predetermined protocol to transmit the packet.

Abstract: An entropy decoder is configured to, for horizontal and vertical components of motion vector differences, derive a truncated unary code from the data stream using context-adaptive binary entropy decoding with exactly one context per bin position of the truncated unary code, which is common for horizontal and vertical components of the motion vector differences, and an Exp-Golomb code using a constant equi-probability bypass mode to obtain the binarizations of the motion vector differences. A desymbolizer is configured to debinarize the binarizations of the motion vector difference syntax elements to obtain integer values of the horizontal and vertical components of the motion vector differences. A reconstructor is configured to reconstruct a video based on the integer values of the horizontal and vertical components of the motion vector differences.

Abstract: A system uses range and Doppler velocity measurements from a lidar system and images from a video system to estimate a six degree-of-freedom trajectory of a target and generate a three-dimensional image of the target. The system may refine the three-dimensional image by reducing the stochastic components in the transformation parameters between video frame times.

Abstract: Pedestrian-Vehicle safety systems for loading docks are disclosed herein. An example method disclosed herein includes sensing whether a person is within a certain area adjacent a dock face of a loading dock, emitting a first signal in response to sensing the person being present within the certain area, sensing rearward movement of a vehicle toward the dock face, emitting a second signal in response to sensing rearward movement of the vehicle while the person is not present in the certain area, and emitting a third signal in response to sensing both the rearward movement of the vehicle and the person being present within the certain area.

Abstract: This disclosure relates to systems and methods for determining when a user likes a piece of content based, at least in part, on analyzing user responses to the content. In one embodiment, the user's response may be monitored by audio and motion detection devices to determine when the user's vocals or movements are emulating the content. When the user's emulation exceeds a threshold amount the content may be designated as “liked.” In certain instances, a similar piece of content may be selected to play when the current content is finished.

Abstract: Disclosed is monitoring device of monitoring a state of a substrate processing process in a substrate processing apparatus. The monitoring device includes: an imaging unit configured to image a processing state of the substrate processing process; a storage unit; a storage control unit configured to store a moving picture imaged by the imaging unit after adding a time stamp to the moving picture; a group classification unit configured to group a plurality of moving pictures stored in the storage unit into moving pictures of a normal group and moving pictures of a group other than the normal group; and a threshold generation unit configured to generate a threshold for detecting an abnormal moving picture based on the moving pictures of the normal group grouped by the group classification unit.