JOURNAL ARTICLE
Real-time stereo vision using semi-global matching on programmable graphics hardware
Abstract
Extracting depth information from pairs of stereo images in real-time allows interactive 3d operations on live video streams. We present a novel adaptation of the Semi-Global Matching (SGM) Algorithm [Hirschmuller 2005] to graphics processing (GPU) hardware, which operates in real-time and frees the CPU for other tasks. We also present shaders which use the extracted depth information to manipulate the video stream in real time.
Keywords:
Shader Computer science Graphics Computer graphics (images) Graphics hardware Matching (statistics) Computer vision Adaptation (eye) Artificial intelligence Graphics pipeline Stream processing 3D computer graphics Parallel computing
Metrics
24
Cited By
1.81
FWCI (Field Weighted Citation Impact)
2
Refs
0.85
Citation Normalized Percentile
Is in top 1%
Is in top 10%
Citation History
Topics
Advanced Vision and Imaging
Physical Sciences → Computer Science → Computer Vision and Pattern Recognition
Advanced Image Processing Techniques
Physical Sciences → Computer Science → Computer Vision and Pattern Recognition
Robotics and Sensor-Based Localization
Physical Sciences → Engineering → Aerospace Engineering
Related Documents
JOURNAL ARTICLE
Near Real-Time Reliable Stereo Matching Using Programmable Graphics Hardware
Year: 2005 Vol: 1 Pages: 924-931
JOURNAL ARTICLE
Real-time stereo vision: Optimizing Semi-Global Matching
Michael MatthiasJan SalmenJohannes StallkampMarc Schlipsing
Year: 2013 Pages: 1197-1202
BOOK-CHAPTER
A Real-Time Low-Power Stereo Vision Engine Using Semi-Global Matching
Stefan GehrigFelix EberliThomas Meyer
Lecture notes in computer science Year: 2009 Pages: 134-143
JOURNAL ARTICLE
A Scalable High-Performance Hardware Architecture for Real-Time Stereo Vision by Semi-Global Matching
Jaco HofmannJens KorinthAndreas Koch
Year: 2016 Pages: 845-853