A method and system detects and localizes an object by first acquiring a frame of a three-dimensional (3D) scene with a sensor, and extracting features from the frame. The frame are segmented into segments, wherein each segment includes one or more features, and for each segment, searching an object map for a similar segment, and only if there is a similar segment in the object map, registering the segment in the frame with the similar segment to obtain a predicted pose of the object. The predicted poses are combined to obtain the pose of the object, which can be outputted.

A stereo matching apparatus is provided, where according to the stereo matching apparatus according to an exemplary embodiment of the present disclosure, a cost at nodes of a plurality of stages relative to an image of a current scan line is determined by which level among a same level, an upper level and a lower level of a previous stage a cost of same stage of an upper scan line is determined, and whether a cost of the same stage of the upper scan line is determined by other disparities.

Disclosed herein is a detector for determining at least one material property of at least one object. The detector includes at least one projector configured for illuminating the object with at least one illumination pattern including a plurality of illumination features; at least one first camera having at least one first sensor element; at least one second camera having at least one second sensor element; and at least one evaluation device configured for evaluating a first reflection image and the second reflection image.

An image recognition approach employs both computer generated and manual image reviews to generate image tags characterizing an image. The computer generated and manual image reviews can be performed sequentially or in parallel. The generated image tags may be provided to a requester in real-time, be used to select an advertisement, and/or be used as the basis of an internet search. In some embodiments generated image tags are used as a basis for an upgraded image review. A confidence of a computer generated image review may be used to determine whether or not to perform a manual image review.

The present invention embraces a system for measuring the 3D shape of an object using a structured light projector and an image sensor such as a scanner or camera. The structured light projector projects a pseudo random dot pattern onto the object that is positioned on a planar surface. The image sensor captures the 3D image of the object from the reflective surface and determines the dimensions or shape of the object. The surface displays the projected dot pattern and defines a grid based on the projected dot pattern. The dot pattern comprising a plurality of dots distributed on the grid such that neighboring dots within a certain sub-window size are unique sub-patterns. The neighboring dots are arranged in a staggered grid format relative to one axis of grid.

A method is disclosed for detecting interaction between two or more participants in a meeting, which includes capturing at least one three-dimensional stream of data on the two or more participants; extracting a time-series of skeletal data from the at least one three-dimensional stream of data on the two or more participants; classifying the time-series of skeletal data for each of the two or more participants based on a plurality of body position classifiers; and calculating an engagement score for each of the two or more participants. In addition, a method is disclosed for improving a group interaction in a meeting, which includes calculating, for each of the two or more participants, an individual engagement state based on attitudes of the participant, wherein the individual engagement state is an engagement state of the participant to the meeting including an engaged state and a disengaged state.

An imaging device includes a first camera and a second camera and shoots the same object under different shooting conditions. A shot-image data acquirer of an image analyzer acquires data of two images simultaneously shot from the imaging device. A correcting section aligns the distributions of the luminance value between the two images by carrying out correction for either one of the two images. A correction table managing section switches and generates a correction table to be used according to the function implemented by the information processing device. A correction table storage stores the correction table showing the correspondence relationship between the luminance values before and after correction. A depth image generator performs stereo matching by using the two images and generates a depth image.

A system and method for generating a dynamic sensor array for an augmented reality system is described. A head mounted device includes one or more sensors, an augmented reality (AR) application, and a sensor array module. The sensor array module identifies available sensors from other head mounted devices that are geographically located within a predefined area. A dynamic sensor array is formed based on the available sensors and the one or more sensors. The dynamic sensor array is updated based on an operational status of the available sensors and the one or more sensors. The AR application generates AR content based on data from the dynamic sensor array. A display of the head mounted device displays the AR content.

An image processing method according to the present invention cuts out partial images corresponding to trimming regions, which is specified for multiple viewpoint images of a stereoscopic image obtained by pupil-division-scheme imaging, from the respective viewpoint images, generates a stereoscopic partial image including multiple partial images, generates parallax information that indicates the parallax between the partial images, adjusts the parallax between the partial images based on the parallax information, and then, for the partial images after the parallax adjustment, enhances the sharpness as the adjusted parallax amount decreases and reduces the sharpness as the adjusted parallax amount increases.

A plurality of processes for emphasizing a stereoscopic effect of an image is supposed and a plurality of stereoscopic effect emphasis processes is integrated in a mode suitable for the image. An image processing device is provided with a stereoscopic effect emphasis processing unit and an integration processing unit. The stereoscopic effect emphasis processing unit executes a plurality of stereoscopic effect emphasis processes on an input image. The integration processing unit integrates results of a plurality of stereoscopic effect emphasis processes according to an integration coefficient used when a plurality of stereoscopic effect emphasis processes is integrated obtained by analyzing the input image. This may be further provided with an image analyzing unit which analyzes the input image to generate the integration coefficient used when a plurality of stereoscopic effect emphasis processes is integrated.