Abstract: A method for a computing device to recalibrate a multiple camera system includes collecting calibration data from one or more pictures captured by the multiple camera system of the computing device. The multiple camera system includes two or more cameras that are each physically separated by a distance from one another. The method further includes detecting decalibration of the camera system. The method further includes, when the camera system is decalibrated, generating recalibration parameters based on the calibration data. The method further includes determining whether the recalibration parameters are valid parameters and, when they are, updating the multiple camera system based on the recalibration parameters.

Abstract: A method for calibrating a camera group includes: controlling a first and second cameras to capture first and second images of a first scene, the first camera having a first field of view (FOV), the second camera having a second FOV overlapping the first FOV in a first overlap region; the first scene including a calibration target in the first overlap region; computing a first relative pose based on the first and second images; controlling the second camera and a third camera to capture third and fourth images of a second scene, the third camera having a third FOV overlapping the second FOV in a second overlap region, the second scene including a calibration target in the second overlap region; computing a second relative pose based on the third and fourth images; and computing a third relative pose based on the first and second relative poses.

Abstract: A method for classifying physical objects includes: controlling, by a processor, one or more depth cameras to capture depth images of a query object; controlling, by the processor, one or more color cameras to capture a color images of the query object; computing, by the processor, a three-dimensional (3D) model of the query object using the depth images; combining, by the processor, the color images with the 3D model; computing, by the processor, a descriptor from the 3D model and the color images, the descriptor including: a multi-dimensional shape descriptor space representation of a 3D shape of the query object; a multi-dimensional color descriptor space representation of a texture of the query object; and a one-dimensional size descriptor space representation of a size of query object; supplying, by the processor, the descriptor to a classifier to compute a classification of the query object; and outputting the classification of the query object.

Abstract: A method for generating a three-dimensional model of an object, by a scanning system including a client-side device including: an acquisition system configured to capture images; and an interaction system including a display device and a network interface includes: capturing a plurality of images of the object by the acquisition system, the images being captured from a plurality of different poses of the acquisition system; computing depth maps from the images of the objects, each of the depth maps corresponding to one of the poses of the acquisition system; combining the depth maps to generate a combined point cloud; and displaying, on the display device, the combined point cloud or a 3D mesh model generated from the combined point cloud.

Abstract: A method for identifying and tracking objects includes: capturing one or more 3-D models of one or more objects in a scene using a three-dimensional (3-D) scanning system, the one or more 3-D models including color and geometry information of the one or more objects; and computing, by an analysis agent, one or more descriptors of the one or more 3-D models, each descriptor corresponding to a fixed-length feature vector; and retrieving metadata identifying the one or more objects based on the one or more descriptors.

Abstract: According to one embodiment of the present invention, a method for automatically generating metadata for a media document includes: computing a feature vector of the media document using a convolutional neural network; searching a collection of media documents for one or more matching media documents having corresponding feature vectors similar to the feature vector of the media document, each media document of the collection of media documents being associated with metadata; generating metadata for the media document based on the metadata associated with the one or more matching media documents; and displaying the media document in association with the generated metadata.

Abstract: A method for capturing a depth map includes: controlling a plurality of cameras to capture, concurrently, a plurality of first images during a first exposure interval, each of the cameras concurrently capturing a corresponding one of the first images, the cameras having overlapping fields of view; controlling a projection source to emit light at a first illumination level during the first exposure interval; controlling the cameras to capture, concurrently, a plurality of second images during a second exposure interval, each of the cameras concurrently capturing a corresponding one of the second images; controlling the projection source to emit light at a second illumination level during the second exposure interval, the second illumination level being different from the first illumination level; combining the first images with the second images to generate a depth map; and outputting the depth map.

Abstract: A method for computing a three-dimensional (3D) model of an object includes: receiving, by a processor, a first chunk including a 3D model of a first portion of the object, the first chunk being generated from a plurality of depth images of the first portion of the object; receiving, by the processor, a second chunk including a 3D model of a second portion the object, the second chunk being generated from a plurality of depth images of the second portion of the object; computing, by the processor, a registration of the first chunk with the second chunk, the registration corresponding to a transformation aligning corresponding portions of the first and second chunks; aligning, by the processor, the first chunk with the second chunk in accordance with the registration; and outputting, by the processor, a 3D model corresponding to the first chunk merged with the second chunk.

Abstract: According to one embodiment of the present invention, a method for automatically generating metadata for a media document includes: computing a feature vector of the media document using a convolutional neural network; searching a collection of media documents for one or more matching media documents having corresponding feature vectors similar to the feature vector of the media document, each media document of the collection of media documents being associated with metadata; generating metadata for the media document based on the metadata associated with the one or more matching media documents; and displaying the media document in association with the generated metadata.

Abstract: A method for generating a three-dimensional model of an object, by a scanning system including a client-side device including: an acquisition system configured to capture images; and an interaction system including a display device and a network interface includes: capturing a plurality of images of the object by the acquisition system, the images being captured from a plurality of different poses of the acquisition system; computing depth maps from the images of the objects, each of the depth maps corresponding to one of the poses of the acquisition system; combining the depth maps to generate a combined point cloud; and displaying, on the display device, the combined point cloud or a 3D mesh model generated from the combined point cloud.

Abstract: An optical projection system includes: a laser emitter configured to emit a beam along an emission axis; an optical element having an optical axis non-parallel to the emission axis, the optical element having a back focal length; and a folding optic configured to redirect the beam toward the optical axis, the beam following a folded optical path having: a first section along the emission axis from the laser emitter to the folding optic; and a second section along the optical axis from the folding optic to the optical element, the sum of the lengths of the first and second sections being equal to the back focal length, the length of the first section being a function of a divergence of the beam and the back focal length, and the folding optic having a height along the optical axis configured to redirect substantially the entire beam emitted by the laser emitter.

Abstract: A method for generating a three-dimensional (3D) model of an object includes: capturing images of the object from a plurality of viewpoints, the images including color images; generating a 3D model of the object from the images, the 3D model including a plurality of planar patches; for each patch of the planar patches: mapping image regions of the images to the patch, each image region including at least one color vector; and computing, for each patch, at least one minimal color vector among the color vectors of the image regions mapped to the patch; generating a diffuse component of a bidirectional reflectance distribution function (BRDF) for each patch of planar patches of the 3D model in accordance with the at least one minimal color vector computed for each patch; and outputting the 3D model with the BRDF for each patch.

Abstract: A handheld three-dimensional scanning sensor including: a depth camera; a client communication interface; a controller; and a memory having instructions stored thereon that, when executed by the controller, cause the controller to: control the depth camera to capture an image; and transmit the image over the client communication interface.

Abstract: A method for applying power in a plurality of pulses to the projection source to control the projection source to emit coherent light during an exposure interval comprising at least two sub-intervals, the applied power causing the projection source to have different temperatures during first and second sub-intervals of the at least two sub-intervals; and emitting light from the projection source, wherein the projection source emits light having different wavelengths during the first and second sub-intervals in accordance with the different temperatures of the projection source.

Abstract: A three-dimensional scanning system includes: a camera configured to capture images; a processor; and memory coupled to the camera and the processor, the memory being configured to store: the images captured by the camera; and instructions that, when executed by the processor, cause the processor to: control the camera to capture one or more initial images of a subject from a first pose of the camera; compute a guidance map in accordance with the one or more initial images to identify one or more next poses; control the camera to capture one or more additional images from at least one of the one or more next poses; update the guidance map in accordance with the one or more additional images; and output the images captured by the camera to generate a three-dimensional model.

Abstract: A pattern projection system includes a coherent light source, a repositionable DOE disposed to receive coherent light from said coherent light source and disposed to output at least one pattern of projectable light onto a scene to be imaged by an (x,y) two-dimensional optical acquisition system. Coherent light speckle artifacts in the projected pattern are reduced by rapidly controllably repositioning the DOE or the entire pattern projection system. Different projectable patterns are selected from a set of M patterns that are related to each other by a translation and/or rotation operation in two-dimensional cosine space. A resultant (x,y,z) depth map has improved quality and robustness due to projection of the selected patterns. Three-dimensional (x,y,z) depth data obtained from two-dimensional imaged data including despeckling is higher quality data than if projected patterns without despeckling were used.

Abstract: A method for detecting decalibration of a depth camera system including a first, second, and third cameras having overlapping fields of view in a direction includes: detecting a feature in a first image captured by the first camera; detecting the feature in a second image captured by the second camera; detecting the feature in a third image captured by the third camera, the third camera being non-collinear with the first and second cameras; identifying a first conjugate epipolar line in the second image in accordance with a detected location of the feature in the first image and calibration parameters; identifying a second conjugate epipolar line in the second image in accordance with a detected location of the feature in the third image and the calibration parameters; and calculating a difference between a detected location of the feature in the second image and the first and second conjugate epipolar lines.

Abstract: A system and method for providing a 3D gesture based user interface with haptic feedback is disclosed. A processing system providing the 3D system provides haptic feedback by capturing image data. A gesture is then detected. The detected gesture is then used to determine an appropriate haptic feedback is determined. A signal that indicates the appropriate haptic feedback is generated and provided to a haptic feedback device. The haptic feedback devices then provides the appropriate haptic feedback.

Abstract: A diffractive optical element includes: a first facet configured to perform an expansion optical function; and a second facet configured to perform a collimation optical function and a pattern generation function.

Abstract: A method for detecting decalibration of a depth camera system including a first, second, and third cameras having overlapping fields of view in a direction includes: detecting a feature in a first image captured by the first camera; detecting the feature in a second image captured by the second camera; detecting the feature in a third image captured by the third camera, the third camera being non-collinear with the first and second cameras; identifying a first conjugate epipolar line in the second image in accordance with a detected location of the feature in the first image and calibration parameters; identifying a second conjugate epipolar line in the second image in accordance with a detected location of the feature in the third image and the calibration parameters; and calculating a difference between a detected location of the feature in the second image and the first and second conjugate epipolar lines.