Post has attachment
CVPR 2016: HYPERDEPTH: LEARNING DEPTH FROM STRUCTURED LIGHT WITHOUT MATCHING

A new structured light #algorithm for fast and precise depth estimation that removes the need for correspondence matching.

Authors:
Sean Ryan Fanello, Christoph Rhemann, Vladimir Tankovich, Adarsh Kowdle, Sergio Orts Escolano, David Kim, Shahram Izadi

Abstract
Structured light sensors are popular due to their robustness to untextured scenes and multipath. These systems triangulate depth by solving a correspondence problem between each camera and projector pixel. This is often framed as a local stereo matching task, correlating patches of pixels in the observed and reference image. However, this is computationally intensive, leading to reduced depth accuracy and framerate. We contribute an algorithm for solving this correspondence problem efficiently, without compromising depth accuracy. For the first time, this problem is cast as a classification-regression task, which we solve extremely efficiently using an ensemble of cascaded random forests. Our algorithm scales in number of disparities, and each pixel can be processed independently, and in parallel. No matching or even access to the corresponding reference pattern is required at runtime, and regressed labels are directly mapped to depth. Our GPU-based algorithm runs at a 1KHz for 1.3MP input/output images, with disparity error of 0.1 subpixels. We show a prototype high framerate depth camera running at 375Hz, useful for solving tracking-related problems. We demonstrate our algorithmic performance, creating high resolution real-time depth maps that surpass the quality of current state of the art depth technologies, highlighting quantization-free results with reduced holes, edge fattening and other stereo-based depth artifacts.


Paper: http://bit.ly/1V0BVSS

Video: https://youtu.be/KJ6_quEHN_0

#Kinect #RealSense #DepthCamera #3D


Post has attachment
Hands - Channel 9 (Microsoft)
http://bit.ly/1sJLOOr

In this episode of 'Context', we take a look at working with #hands starting with some simple ideas around using pointers for #touch, #mouse, #pen and then branching off into the #3D plane with cameras like the #Kinect for Windows V2 and Intel's #RealSense F200 camera.
with Andrew Spooner and Mike Taulty

Here's a breakdown of the show;

[00:00] Hello!
[00:20] Welcome to the show - Faces.
[04:47] Vox Pops
[06:04] Show Me the Code
[27:10] CTRL-Z
[31:20] README.txt

http://bit.ly/1sJLOOr

Post has attachment

Post has attachment
Windows 10 #UWP, Intel #RealSense SR300, First Steps http://bit.ly/1YYtNFU by Mike Taulty
#Windows10 #Intel

Post has attachment

Post has attachment

Post has attachment

Post has attachment
‪#‎Kinect‬ V2, ‪#‎WindowsHello‬ and ‪#‎Perception‬ APIs by Mike Taulty http://bit.ly/1YNrg2d #Intel ‪#‎RealSense‬

Post has attachment
Intel® ‪#‎RealSense‬™ SDK R5 (version 7.0.23.8048) released http://intel.ly/1QtX8Ur ‪#‎F200‬ ‪#‎R200‬ ‪#‎SR300‬ ‪#‎Intel‬ +Intel RealSense 讓你演得有意思

Post has attachment
Wait while more posts are being loaded