Abstract: Embodiments of the present disclosure provide a method and apparatus for detecting a target object in an image. The method includes: performing following prediction operations using a pre-trained neural network: detecting a target object in a two-dimensional image to determine a two-dimensional bounding box of the target object; and determining a relative position constraint relationship between the two-dimensional bounding box of the target object and a three-dimensional projection bounding box obtained by projecting a three-dimensional bounding box of the target object into the two-dimensional image; and the method further including: determining the three-dimensional projection bounding box of the target object, based on the two-dimensional bounding box of the target object and the relative position constraint relationship between the two-dimensional bounding box of the target object and the three-dimensional projection bounding box.

Abstract: A system for spatially mapping neurons in brain tissue is disclosed which includes a source of light configured to be shone on a subject at a first wavelength causing emission of light at a second wavelength from generating calcium when one or more neurons are firing, an optical filter configured to allow passage of light having the second wavelength, an image capture device configured to capture images of the brain tissue at the second wavelength, and a processor with software configured to establish a spatial model for localizing one or more neurons where captured images are used to iteratively adjust parameters of the model to thereby minimize error between generated and captured images.

Abstract: A method for identifying a source of florescence is disclosed which includes shining light on a subject at a first wavelength, causing emission of light at a second wavelength from the source of fluorescence, filtering out light at the first wavelength, capturing at least one 2 dimensional (2D) image of a subject having a plurality of pixels at the second wavelength, and establishing information about approximate location of a source of florescence within a tissue of the subject, selectively generating a 3D geometric model where the model is adapted to provide a model representation of the at least one 2D captured image, comparing the modeled at least one 2D captured image to the captured at least one 2D image and iteratively adjusting the model to minimize the difference, and outputting location and geometric configuration of the source of fluorescence within the tissue within the region of interest.

Abstract: A smart device is provided with an application program for displaying a video feed received from the smart device's camera. The application can determine the coordinates for an intersection point, which is a point on the ground where the smart device is pointing at. The application can display a target on the visual representation of the intersection point. Based on whether the smart device is at an appropriate distance from the intersection point, the user interface can superimpose an indicator on the video feed received from the camera. This can inform the user whether the smart device is at an optimal scan distance from the intersection point (or an object) so that the object can be identified by a machine learning model.

Abstract: A stereoscopic visualization system using shape from shading algorithm is an image conversion device connected between a monoscopic endoscope and a 3D monitor. The system applies the algorithm which generates a depth map for a 2D image of video frames. The algorithm first calculates a direction of a light source for the 2D image. Based upon the information of light distribution and shading for the 2D image, the depth map is generated. The depth map is used to calculate another view of the original 2D image by depth image based rendering algorithm in generation of stereoscopic images. After the new view is rendered, the stereoscopic visualization system also needs to convert the display format of the stereoscopic images for different kinds of 3D displays. Based on this method, it can replace the whole monoscopic endoscope with a stereo-endoscope system and no modification is required for the monoscopic endoscope.

Abstract: A method of measuring a height of a vehicle on a road comprises recording with a vehicle classification sensor a 3D representation of the vehicle passing the section and recording with a camera a 2D image of at least an upper portion of the vehicle and a background; determining an edge profile between the upper portion and the background establishing a fan of rays each extending from the elevated point and through a different one of multiple points along the edge profile; shifting the 3D representation in the coordinate system in height until it is tangent to said fan; and determining said height of the vehicle from the shifted 3D representation in the coordinate system. The disclosed subject matter further relates to an apparatus for performing this method.

Abstract: A holographic display device for presenting a hologram-like image and a method of use are disclosed. The holographic display device includes a box-like structure, a translucent panel, and light panels extending the entire length of the box-like structure. The light panels position between the box-like structure and the translucent panel. The holographic display device includes a transparent monitor connecting the box-like structure at its front end. The transparent monitor receives and displays an image. The light panels illuminate light and the translucent panel diffuses, blends, and evenly distributes the light in the interior. Transmitted shadowing to the monitor provides a realistic appearance. A unique image capturing system for capturing the image to be displayed on the transparent monitor is also disclosed. The image capturing system transmits the image to the holographic display device in real-time or as a pre-recorded image using wired or wireless protocols.

Abstract: Systems and methods for a dense surface reconstruction of an object using graph signal processing is provided. None of the traditional systems and methods provide for a dense or three-dimensional surface reconstruction of objects by resolving ? ambiguity. The embodiments of the proposed disclosure provide for resolving ? ambiguity by identifying, from one or more sparse three-dimensional shapes extracted, a first set of azimuth values corresponding to a first region of the object; constructing, using a phase angle, a graph capturing a relational structure between the first set of azimuth values and a second set of azimuth values to be estimated; obtaining, a Graph Fourier Transform (GFT) matrix corresponding to the constructed graph; and estimating, from the GFT matrix and the first set of azimuth values, the second set of azimuth values corresponding to a second region of the object by the graph signal processing technique.

Abstract: A method includes receiving a first image and a second image, wherein the first and second images represent first and second relative locations, respectively, of an image acquisition device with respect to a subject. The method also includes determining, using the first and second images, a total relative displacement of the subject with respect to the image acquisition device between a time of capture of the first image and a time of capture of the second image, and determining, based on sensor data associated with one or more sensors associated with the image acquisition device, a component of the total relative displacement associated with a motion of the image acquisition device. The method also includes determining, based on a difference between the first total relative displacement and the component, that the first subject is an alternative representation of a live person, and in response, preventing access to a secure system.

Abstract: An information processing apparatus has a hold unit for holding a plurality of features of a physical space as a plurality of held features, each of the plurality of held features being related with a position in a first image captured by an image capturing apparatus at a first time, and information of an availability for a position/orientation calculation of the image capturing apparatus. The information processing apparatus associates a plurality of detected features, which are detected in a second image captured by the image capturing apparatus at a second time after the first time, with the plurality of held features, and, based on the availabilities related with the associated held features, adjusts a detected feature, among the plurality of detected features, to be used in the calculation of the position/orientation of the image capturing apparatus.

Abstract: An image processing method includes: detecting a first quadrangle in an image, where the first quadrangle includes four vertexes, the four vertexes correspond to four photographed points; determining distance information of the four photographed points relative to a camera capturing the image; determining locations of the four photographed points based on the distance information of the four photographed points and location information of the points on the image; and determining, based on the locations of the four photographed points, that the four photographed points are coplanar, where the four photographed points form a second quadrangle, determining a side ratio of two neighboring sides of the second quadrangle when a side angle and a side length relationship of the second quadrangle satisfy a preset condition, and correcting the first quadrangle to a rectangle, where two neighboring sides of the rectangle are in the side ratio.

Abstract: A method and system for 3D modeling of a construction or structure based on producing a 3D image from digital 2D images of the construction or structure, transforming the 3D image to a data point cloud presentation, electing a collection of data points, identifying an object of the construction or structure that matches the collection of data points, attaching corresponding visual images to a record of the identified object and repeating these steps for any collection of data points until completing the construction of a 3D model based on a combination of all identified objects. This 3D modeling is based on photos obtained from digital photographing means mounted on a UAV (Unmanned Aerial Vehicle) and launched to survey the construction or structure.

Abstract: A moving body position information recognition display device includes a traveling state obtaining part for obtaining information on a traveling state of a host moving body. An object information obtaining part for obtaining information on a plurality of objects including a shape of a travel road and another moving body. A virtual space construction part for constructing a virtual space by associating at least the host moving body and each of the plurality of objects with each of a plurality of virtual models and by arranging the associated virtual models in a three-dimensional space. A two-dimensional video generation part for generating a two-dimensional video capturing the virtual space from a virtual camera arranged in the virtual space and output the two-dimensional video. The two-dimensional video generation part generates the two-dimensional video while adding a predetermined effect to the virtual model corresponding to the object in the two-dimensional video.

Abstract: Systems and techniques are described for interaction plane rotation for manipulation of three-dimensional objects. A three-dimensional object can be displayed as a two-dimensional representation of the object, represented on an interaction plane and intersected by an object view vector that represents a point of view of the object through a viewing plane. An angle between the object view vector and the interaction plane is calculated and compared to a threshold value. A determination is made that the calculated angle is less than the threshold value, and a rotation magnitude that defines an amount of rotation of the interaction plane relative to a constant vector is calculated. The interaction plane is rotated relative to the constant vector in a rotation direction by the rotation magnitude. The rotated interaction plane can then be used to determine an intended relative movement between the object view vector and the three-dimensional object.

Abstract: A method for generating spatial-temporal consistency depth map sequences based on convolutional neural networks for 2D-3D conversion of television works includes steps of: 1) collecting a training set, wherein each training sample thereof includes a sequence of continuous RGB images, and a corresponding depth map sequence; 2) processing each image sequence in the training set with spatial-temporal consistency superpixel segmentation, and establishing a spatial similarity matrix and a temporal similarity matrix; 3) establishing the convolution neural network including a single superpixel depth regression network and a spatial-temporal consistency condition random field loss layer; 4) training the convolution neural network; and 5) recovering a depth maps of a RGB image sequence of unknown depth through forward propagation with the trained convolution neural network; which avoids that clue-based depth recovery method is greatly depended on scenario assumptions, and inter-frame discontinuity between depth maps g

Abstract: An imagery system includes: a camera having a field of view; a light source including a source of structured light, the light source movable relative to the camera; and at least one processor. The at least one processor is programmed to determine, at least, estimated locations of points on a surface exposed to the structured light according to image data received from the field of view of the camera. The light source may include at least one fiducial marker, and the at least one processor may be programmed to determine the estimated position of the source of structured light according to the at least one fiducial marker in the image data. Also, the camera may be a stereoscopic camera.

Abstract: An ambient animation system, including an image sensor configured to capture an image of an environment outside of a vehicle, a display interface configured to display information to a driver of the vehicle, and a controller in communication with the image sensor and the display interface and configured to generate a virtual spherical lighting object, shape the image to fit around the virtual spherical lighting object, and project a portion of the image fitted around the virtual spherical lighting object onto the display interface.

Abstract: A lens device for an illumination assembly. The lens device has light-entry and light-exit surfaces and comprises at least one ring region. Each ring region extends along a circumferential direction about a central axis of the lens device, and comprises a plurality of area segments. Each area segment forms a circular arc portion of a respective ring region and comprises a first end in the circumferential direction and a second end opposite to the first end in the circumferential direction. At the first end, the light-exit surface is inclined in the direction of the central axis by an arbitrary first angle in relation to the light-entry surface, and at the second end, the light-exit surface is inclined in the direction of the central axis by an arbitrary second angle in relation to the light-entry surface differing from the first angle.

Abstract: A camera monitoring system for a vehicle includes a plurality of cameras disposed around an exterior of a vehicle. An image processing module communicates with the plurality of cameras, generating overhead view images from raw images taken by at least one of the plurality of cameras. A histogram module communicates with the image processing module, generating at least one histogram from the overhead view images. A likelihood module communicates with the histogram module and determines a likelihood of blockage for at least one of the plurality of cameras. A line alignment module communicates with the likelihood module and the image processing module to determine whether a trajectory of detected feature points in a selected camera aligns with a trajectory of detected feature points in an adjacent camera. A reporting module communicates with the line alignment module and reports a camera blockage status to at least one vehicle system or controller.

Abstract: Methods and apparatus for producing multi-view 3D renderings of a scene, and collaboratively sharing information related to the renderings to facilitate producing synthetic viewpoints of the scene. In one example, a method of producing a 3D synthetic viewpoint of the scene includes receiving an image of the scene from a local camera, analyzing the image to determine a context of the scene and to extract at least one surface feature of the scene, developing an initial set of planar world coordinates for the image based on the at least one surface feature to estimate an initial local perspective projection matrix, and mapping image pixels of the image to a world plane to produce the 3D synthetic viewpoint of the scene by using the initial local perspective projection matrix to map image space coordinates to world coordinates.

Abstract: A camera module is provided. The camera module includes a number of camera assembles. Each of the camera assembles includes a lens unit and an electromagnetic driving unit. The electromagnetic driving unit includes at least one magnetic element for controlling the movement of the corresponding lens unit. The distance between two of the magnetic elements, which are closest to each other and respectively positioned in two of the camera assemblies, is greater than the distance between two of the light through holes, to which the two of the camera assemblies are arranged to correspond.

Abstract: An image processing system according to the present embodiment includes a generating unit and a display controlling unit. The generating unit generates a group of different types of parallax image sets that are to three-dimensionally display an object onto the display surface of the displaying unit, from different types of three-dimensional medical image data generated by performing different types of image processing onto imaging data of the object collected by a medical image diagnosis apparatus. The display controlling unit performs control so that display conditions of the group of different types of parallax image sets are switched in accordance with the switching of the viewpoint position around the object displayed on the display surface and that the group of different types of parallax image sets are superimposed and displayed.

Abstract: Systems and methods for enhancement of a coupled zone of a 3D stereoscopic display. The method may include determining a size and a shape of the coupled zone. The coupled zone may include a physical volume specified by the user's visual depth of field with respect to screen position of the 3D stereoscopic display and the user's point of view. Content may be displayed at a first position with a virtual 3D space and the first position may correspond to a position within the coupled zone. It may be determined that the content is not contained in the coupled zone or is within a specified distance from a boundary of the coupled zone and, in response, display of the content may be adjusted such that the content has a second position in the virtual 3D space that corresponds to another position within the coupled zone.

Abstract: A display device includes a display portion, an input portion that receives an instruction to select a program in a program list such that the display portion displays the program with a distinguishable expression, and a controller that links a first program having a program duration shorter than a predetermined threshold with at least one second program arranged relative to the first program along a time axis of the program list as a linked program, and that controls the display portion to display the linked program with the distinguishable expression.

Abstract: Systems and methods for conducting autonomous underwater inspections of subsea and other underwater structures using a 3D laser mounted on an underwater platform such as AUV, an ROV or a tripod. The systems and methods described herein can be used for scanning underwater structures to gain a better understanding of the underwater structures, such as for example, for the purpose of avoiding collision of an underwater vehicle with the underwater structures and for directing inspection, repair, and manipulation of the underwater structures.

Abstract: An exemplary method includes prompting a user to capture video data at a location. The location is associated with navigation directions for the user. Information representing visual orientation and positioning information associated with the captured video data is received by one or more computing devices, and a stored data model representing a 3D geometry depicting objects associated with the location is accessed. Between corresponding images from the captured video data and projections of the 3D geometry, one or more candidate change regions are detected. Each candidate change region indicates an area of visual difference between the captured video data and projections. When it is detected that a count of the one or more candidate change regions is below a threshold, the stored model data is updated with at least part of the captured video data based on the visual orientation and positioning information associated with the captured video data.

Abstract: A system adapted to implement a learning rule in a three-dimensional (3D) environment is described. The system includes: a renderer adapted to generate a two-dimensional (2D) image based at least partly on a 3D scene; a computational element adapted to generate a set of appearance features based at least partly on the 2D image; and an attribute classifier adapted to generate at least one set of learned features based at least partly on the set of appearance features and to generate a set of estimated scene features based at least partly on the set of learned features. A method labels each image from among the set of 2D images with scene information regarding the 3D scene; selects a set of learning modifiers based at least partly on the labeling of at least two images; and updates a set of weights based at least partly on the set of learning modifiers.

Abstract: A three dimensional (3D) video data processing method in a broadcast transmitter includes encoding, by an encoder, 3D video data which carries a first image and a second image in separate video streams; generating, by a system information processor, system information comprising 3D video composition information about the 3D video data; multiplexing, by a multiplexer, the system information and the 3D video data; and transmitting, by a transmitting unit, a broadcast signal carrying the 3D video data and the system information. The 3D video composition information includes first information on resolution of the 3D video data.

Abstract: A method of rendering views for a multi-view display device (100) is disclosed. The multi-view display device (100) comprises a number of display means (104, 110) for displaying respective views in mutually different directions relative to the multi-view display device (100). The method comprises: computing a first motion vector field on basis of a first input image of a time sequence of input images and a second input image of the time sequence of input images; computing a first motion compensated intermediate image on basis of the first motion vector field, the first input image and/or the second input image; and providing the first motion compensated intermediate image to a first one of the number of display means (104, 110).

Abstract: Adjusting overlay positioning in stereoscopic video, including: receiving overlay data including a plurality of overlays, each overlay having a lateral axis value, a vertical axis value, and a depth value; receiving and displaying the stereoscopic video to a user as at least one of a video preview display and a stereoscopic display, each display including an overlay from the overlay data, wherein a position of the overlay in each display is based on the lateral axis value, the vertical axis value, and the depth value of the overlay, and wherein the video preview display includes interfaces for adjusting the position of the overlay in each display; receiving input from the user related to the depth value of the overlay; and adjusting the position of the overlay in the video preview display based on the input from the user.

Abstract: [Object] To maintain perspective consistency among individual objects in an image in superimposition display of a caption (caption unit) in an ARIB method. [Solution] A multiplexed data stream including a video data stream and a caption data stream is transmitted from a broadcast station to a set top box. A video data stream supplied from a video encoder 113 includes stereo image data. A caption data stream supplied from a caption encoder 133 includes data of captions (caption units) in the ARIB method serving as superimposition information and disparity information (disparity information set). In the caption data stream, the pieces of data of a certain number of captions that are to be displayed on the same screen are sequentially arranged via a separator.

Abstract: Provided is a method and apparatus for linear depth mapping. Linear depth mapping includes using algorithms to correct the distorted depth mapping of stereoscopic capture and display systems.

Abstract: Implementations of the present invention involve methods and systems for creating depth and volume in a 2-D planar image to create an associated 3-D image by utilizing a plurality of layers of the 2-D image, where each layer comprises one or more portions of the 2-D image. Each layer may be reproduced into a corresponding left eye and right eye layers, with one or both layers including a pixel offset corresponding to a perceived depth. Further, a depth model may be created for one or more objects of the 2-D image to provide a template upon which the pixel offset for one or more pixels of the 2-D image may be adjusted to provide the 2-D image with a more nuanced 3-D effect. In this manner, the 2-D image may be converted to a corresponding 3-D image with a perceived depth.

Abstract: The recorder apparatus includes the controller that sets conversion mode used when input stream is processed and converted into recording stream to any of two-dimensional mode that converts the input stream into two-dimensional recording stream and three-dimensional mode that converts the input stream into three-dimensional recording stream, the controller that sets one recording mode that can be used when the video signal is converted and processed in the two-dimensional mode and the three-dimensional mode and specifies recording rate, and the signal processor that processes the video signal based on the set conversion mode and the set recording mode to convert the video signal into recording video signal. The controller sets the recording modes such that combination of the recording modes that can be set when the two-dimensional mode is set is different from combination of recording modes that can be set when the three-dimensional mode is set.

Abstract: Stereo imaging can be provided on an electronic device without the need for two matched, high resolution, large format cameras. In various embodiments, two or more cameras of disparate types can be used to capture stereoscopic images. Various processing algorithms can be used to adjust aspects such as the effective pixel size and depth of focus in order to provide for sufficient information to generate three-dimensional images without significant artifacts resulting from differences in the mismatched cameras.

Abstract: Disclosed is an LCD device which facilitates to improve picture quality of two-dimensional (2D) and three-dimensional (3D) images by automatically converting an image driving mode (2D/3D) in accordance with a viewing distance, and a method for driving the same, wherein the device comprises a distance measuring unit which measures a viewing distance between the LCD device and a viewer; an image mode controller which sets a 2D image mode or 3D image mode in accordance with a comparison result between the viewing distance and a preset reference distance; a timing controller which aligns externally-provided image signals in accordance with the 2D image mode or 3D image mode set by the image mode controller, and converts the aligned image signals into image data by frame unit; and a liquid crystal panel which displays an image based on the 2D image mode or 3D image mode.

Abstract: Margins are prevented from being produced when the amount of parallax of a stereoscopic image has been enlarged. A parallax adjustment command is applied if a stereoscopic image is displayed in an image compositing area that has been defined on a page constituting an electronic album. The amount of parallax is enlarged in response to application of a command to enlarge the amount of parallax. If enlarging the amount of parallax will cause margins to be produced when the stereoscopic image is displayed in the image compositing area on the page, then this page is replaced by a page on which an image compositing area that will not produce margins has been formed.

Abstract: A system that runs in web browsers of mobile devices that allows mobile users to take photos of building exteriors and interiors or other real world objects, upload photos, share photos with others, and use the photo images to model the 3D models with the system's image-based modeling interface.

Abstract: A processor includes: an imaging control unit which causes an imaging unit for capturing an image with changing a focused object distance, to change the focused object distance with a first change width in the case of a first focused object distance, and to change the focused object distance with a second change width that is smaller than the first change width in the case of a second focused object distance that is shorter than the first focused object distance; and an image processing unit which extracts focused object image data from captured image data for each of the focused object distances, and generates image data by shifting the extracted object image data by parallax amounts corresponding to the respective focused object distances, and by synthesizing the extracted object image data.

Abstract: Tools are described for preparing digital dental models for use in dental restoration production processes, along with associated systems and methods. Dental modeling is improved by supplementing views of three-dimensional models with still images of the modeled subject matter. Video data acquired during a scan of the model provides a source of still images that can be displayed alongside a rendered three-dimensional model, and the two views (model and still image) may be synchronized to provide a common perspective of the model's subject matter. This approach provides useful visual information for disambiguating surface features of the model during processing steps such as marking a margin of a prepared tooth surface for a restoration.

Abstract: A disparity vector for a pixel in a right image corresponding to a pixel in a left image in a pair of stereo images is determined. The disparity vector is based on a horizontal disparity and a vertical disparity and the pair of stereo images is unrectified. First, a set of candidate horizontal disparities is determined. For each candidate horizontal disparity, a cost associated with a particular horizontal disparity and corresponding vertical disparities is determined. The vertical disparity associated with a first optimal cost is assigned to each candidate horizontal disparity, so that the candidate horizontal disparity and the vertical disparity yield a candidate disparity vector. Lastly, the candidate disparity vector with a second optimal cost is selected as the disparity vector of the pixel in the right image.

Abstract: A time-of-flight 3D camera and related method for illuminating a camera field of view and capturing return image light are disclosed herein. In one example, the time-of-flight 3D camera includes a light source that emits source light along an optical axis, and a collimator that receives and collimates the source light to create collimated light. A refractive diffuser is tuned to the camera field of view and receives and diffuses the collimated light to create refracted light having a varying intensity profile. The refractive diffuser guides the refracted light to illuminate the camera field of view to reduce wasted source light.

Abstract: There is provided a demultiplexer that receives video data for one of a three-dimensional display and a two-dimensional display. There is also provided an HDMI transmission portion that transmits the video data and display information that pertains to one of the three-dimensional display and the two-dimensional display of the video data to a television receiver through TMDS channels #0, #1, and #2 of an HDMI cable. There is also provided a transmission/receiving portion that transmits the display information to the television receiver through a CEC line of the HDMI cable.

Abstract: Objects within two-dimensional (2D) video data are modeled by three-dimensional (3D) models as a function of object type and motion through manually calibrating a 2D image to the three spatial dimensions of a 3D modeling cube. Calibrated 3D locations of an object in motion in the 2D image field of view of a video data input are computed and used to determine a heading direction of the object as a function of the camera calibration and determined movement between the computed 3D locations. The 2D object image is replaced in the video data input with an object-type 3D polygonal model having a projected bounding box that best matches a bounding box of an image blob, the model oriented in the determined heading direction. The bounding box of the replacing model is then scaled to fit the object image blob bounding box, and rendered with extracted image features.

Abstract: A 3D image processing apparatus includes: L and R graphic decoders which decode coded stream data to generate left-eye and right-eye image data; an image output control unit which outputs the generated image data; and a control unit which, when a decoding error occurs in generating one of the image data, and a successful decode occurs in generating the other of the image data, (i) shifts, by a preset offset, a pixel position of the other of the image data, to generate pseudo image data as the one of the image data, and (ii) outputs the pseudo image data to an image output control unit, wherein the image output control unit outputs the other of the image data and the pseudo image data, when the decoding error occurs in generating the one of the image data and the successful decode occurs in generating the other of the image data.

Abstract: A mirror assembly adapted for use in a panoramic imaging system for capturing a panoramic image includes a mirror for optically coupling to a fisheye lens having a first field of view, the mirror configured for reflecting an image of a second field of view through the fisheye lens. A housing has a first end and a second end, the mirror being secured proximate to the first end, and the second end having an engagement portion for securing the mirror assembly to the panoramic imaging system. When the mirror assembly is secured to the panoramic imaging system, the mirror is optically coupled to the fisheye lens and a detector for capturing a first portion of the panoramic image and a second portion of the panoramic image, the first portion of the panoramic image having a portion overlapping the second portion of the panoramic image.

Abstract: According to one embodiment, a depth signal generating apparatus includes following units. The calculating unit is configured to calculate a statistic value for pixel values for each of predefined areas in the first image, and calculate, for each of predetermined base depth models, a first evaluation value based on the calculated statistic value. The correcting unit is configured to correct, based on a second evaluation value previously derived for the second image and a first degree of similarity indicating a similarity between the predetermined base depth models, the first evaluation value to derive second evaluation values for the predetermined base depth models. The selecting unit is configured to select a base depth model having the highest second evaluation value from the predetermined base depth models. The generating unit is configured to generate a depth signal based on the selected base depth model.

Abstract: In an example, a method of decoding video data includes determining whether a reference index for a current block corresponds to an inter-view reference picture, and when the reference index for the current block corresponds to the inter-view reference picture, obtaining, from an encoded bitstream, data indicating a view synthesis prediction (VSP) mode of the current block, where the VSP mode for the reference index indicates whether the current block is predicted with view synthesis prediction from the inter-view reference picture.

Abstract: An apparatus and method for computing a three dimensional model of a surface of an object are disclosed. At least one directional energy source (106-109) directionally illuminates the object (101). An imaging assembly (104), having at least two spatially separated viewpoints (111,112) at fixed positions relative to each other, records a series of images of the object at each viewpoint when the object is illuminated by the source. At least one localisation template (102,103) having predetermined geometrical features is visible to at least one of the viewpoints simultaneously with the object. The images recorded at the viewpoints are analysed so as to determine the location and pose of each viewpoint relative to the template for each image in the series of images. Photometric data for the object is generated using the calculated location and pose of the viewpoints and the image data.

Abstract: An image processing system includes at least two, complementary, angle sensitive pixel (ASP) structures, having a spatial frequency domain ASP output including a background output and a plurality of ASP response outputs, in response to an optical input; an ASP response output subtractor component, which functions to suppress the background output and perform a subtraction of at least two of the ASP response outputs; and a processing component that can process the subtracted spatial frequency domain ASP response outputs. An optical domain image processing method includes the steps of providing at least two, complementary, angle sensitive pixel (ASP) structures; obtaining a spatial frequency domain ASP output including a plurality of complementary ASP response outputs, in response to an optical input; performing a wavelet-like transform of the ASP response outputs in the optical domain prior to performing any operation in a digital domain; and obtaining a desired output of the optical input.