scispace - formally typeset
Patent

Depth camera based on structured light and stereo vision

TLDR
In this article, a depth camera system uses a structured light illuminator and multiple sensors such as infrared light detectors, such as in a system which tracks the motion of a user in a field of view.
Abstract
A depth camera system uses a structured light illuminator and multiple sensors such as infrared light detectors, such as in a system which tracks the motion of a user in a field of view. One sensor can be optimized for shorter range detection while another sensor is optimized for longer range detection. The sensors can have a different baseline distance from the illuminator, as well as a different spatial resolution, exposure time and sensitivity. In one approach, depth values are obtained from each sensor by matching to the structured light pattern, and the depth values are merged to obtain a final depth map which is provided as an input to an application. The merging can involve unweighted averaging, weighted averaging, accuracy measures and/or confidence measures. In another approach, additional depth values which are included in the merging are obtained using stereoscopic matching among pixel data of the sensors.

read more

Citations
More filters
Patent

Dynamic adjustment of light source power in structured light active depth sensing systems

TL;DR: In this paper, a method and device is provided that compensates for different reflectivity/absorption coefficients of objects in a scene/object when performing active depth sensing using structured light.
Patent

Combined depth filtering and super resolution

TL;DR: In this paper, a depth pixel of the depth map is initially assigned a confidence value based on curvature values and localized contrast information, and then a new depth value is assigned based on an extrapolation of depth values associated with neighboring pixel locations.
Patent

Encoding and decoding virtual reality video

TL;DR: In this article, a virtual reality or augmented reality experience of a scene may be decoded for playback for a viewer through a combination of CPU and GPU processing, where a video stream may be retrieved from a data store and a first viewer position and orientation may be received from an input device, such as the sensor package on a head-mounted display (HMD).
Patent

Motion tracking system for real time adaptive motion compensation in biomedical imaging

TL;DR: In this paper, a motion tracking system is configured to overlay tracking data over biomedical imaging data in order to display the tracking data along with its associated image data, and one or more detectors are configured to detect images of a patient, and a detector processing interface is configured for analyzing the images to estimate motion or movement of the patient and to generate tracking data describing the patient's motion.
Patent

Methods and systems for generating depth data by converging independently-captured depth maps

TL;DR: In this paper, the first and second depth maps of a real-world scene are obtained independently using first-and second-level depth map capture techniques, respectively, and a third depth data point representing the physical point on the surface of the object is generated.
References
More filters
Journal ArticleDOI

A multiple-baseline stereo

TL;DR: It is shown that the SSSD-in-inverse-distance function exhibits a unique and clear minimum at the correct matching position, even when the underlying intensity patterns of the scene include ambiguities or repetitive patterns.
Patent

Apparatus and methods for determining the three-dimensional shape of an object using active illumination and relative blurring in two images due to defocus

TL;DR: In this article, a method and apparatus for mapping depth of an object in a preferred arrangement uses a projected light pattern to provide a selected texture to the object along the optical axis (24) of observation.
Patent

3d geometric modeling and motion capture using both single and dual imaging

TL;DR: In this article, a bi-dimensional coded light pattern is projected on the object such that each of the identifiable feature types appears at most once on predefined sections of distinguishable epipolar lines.
Patent

3d geometric modeling and 3d video content creation

TL;DR: In this paper, a bi-dimensional coded light pattern is projected on the object such that each of the identifiable feature types appears at most once on predefined sections of distinguishable epipolar lines.
Patent

Vision system for an autonomous vehicle

TL;DR: In this article, a stereo vision system using a combination of cameras having > a wide baseline in order to detect obstacles that are relatively far away from the cameras and > a shorter baseline to detect obstacle that are closer to the cameras is presented.