761 Hits in 5.8 sec

Real-Time Stereo Vision on FPGAs with SceneScan [article]

Konstantin Schauwecker
2018 arXiv   pre-print
The implementation uses a variation of the Semi-Global Matching (SGM) algorithm, which provides superior results compared to many simpler approaches.  ...  With this implementation we have created two stand-alone hardware systems for stereo vision, called SceneScan and SceneScan Pro.  ...  The stereo matching method that is implemented in SceneScan / SceneScan Pro is based on Semi Global Matching (SGM) [9] .  ... 
arXiv:1809.07977v1 fatcat:v7pn7tg2ijazjfdylob6iiihv4

Stereo depth with a Unified Architecture GPU

Joel Gibson, Oge Marques
2008 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
The Compute Unified Device Architecture (CUDA) from NVIDIA was employed in novel ways to compute depth using BT cost matching and the Semi-Global Matching algorithm.  ...  This paper describes how the calculation of depth from stereo images was accelerated using a GPU.  ...  An exception which stood out was Hirschmüller's Semi-Global Matching(SGM) (10) .  ... 
doi:10.1109/cvprw.2008.4563092 dblp:conf/cvpr/GibsonM08 fatcat:kmbajopvgnbsvopuhm47vckzvu

A Survey of FPGA-Based Robotic Computing [article]

Zishen Wan, Bo Yu, Thomas Yuang Li, Jie Tang, Yuhao Zhu, Yu Wang, Arijit Raychowdhury, Shaoshan Liu
2021 arXiv   pre-print
Recent researches on robotics have shown significant improvement, spanning from algorithms, mechanics to hardware architectures.  ...  On the one hand, CPU platform is flexible to handle multiple robotic tasks.  ...  Vision Systems on FPGA platforms, across local stereo matching, global stereo matching, semi-global stereo matching (SGM) and efficient large-scale stereo matching (ELAS) algorithms.  ... 
arXiv:2009.06034v3 fatcat:fnp5q5wcyrd2hgpllso22mv2xm

GPU-Based Optimization of Self-Organizing Map Feature Matching for Real-Time Stereo Vision

Kajal Sharma, Saifullah Saifullah, Inkyu Moon
2014 Journal of information and communication convergence engineering  
The scale invariant feature transform algorithm developed by Lowe for various feature matching applications, such as stereo vision and object recognition, is computationally intensive.  ...  In this paper, we present a graphics processing unit (GPU)-based matching technique for the purpose of fast feature matching between different images.  ...  In a recent research [9] , we have implemented an efficient feature matching technique, which is faster than Lowe's SIFT, with a selforganizing map (SOM) that can be used for real-time stereo matching  ... 
doi:10.6109/jicce.2014.12.2.128 fatcat:fkvc76vjlvelxcdeiptggffod4

Full high-definition real-time depth estimation for three-dimensional video system

Hejian Li, Ping An, Zhaoyang Zhang
2014 Optical Engineering: The Journal of SPIE  
The depth estimation algorithm is especially complex and it is an obstacle for real-time system implementation.  ...  The proposed field-programmable gate array (FPGA)-based architecture implements a fusion strategy matching algorithm for efficiency design.  ...  With the increasing requirements for accuracy and image size, there are two strategies that appear in hardware implementation. One is the semi-global matching (SGM) method.  ... 
doi:10.1117/1.oe.53.9.093108 fatcat:zqetra7yfjft5lwkrn4fxwkyz4

Parallel implementation of real-time semi-global matching on embedded multi-core architectures

Oliver Jakob Arndt, Daniel Becker, Christian Banz, Holger Blume
2013 2013 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (SAMOS)  
For instance, semi-global matching for stereo image processing, including complex data flows, traditionally runs on customized hardware modules.  ...  In this work, we introduce a parallel version of a semi-global matching algorithm and demonstrate within this case study runtime optimizations necessary to meet real-time requirements.  ...  For instance, semi-global matching algorithm for stereo image processing [1] , as a key element in driver assistance including complex data access pattern, traditionally meets real-time constraints only  ... 
doi:10.1109/samos.2013.6621106 dblp:conf/samos/ArndtBBB13 fatcat:uiuzklxgr5ff3nszb75spglzo4

A census-based stereo vision algorithm using modified Semi-Global Matching and plane fitting to improve matching quality

Martin Humenberger, Tobias Engelke, Wilfried Kubinger
2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops  
The quality of the local optimized matches is increased by a modified Semi-Global Matching (SGM) step with subpixel accuracy.  ...  This paper introduces a new segmentation-based approach for disparity optimization in stereo vision.  ...  To the authors' knowledge, no implementation of a global optimization is commercially available for purely embedded real-time platforms without dedicated hardware such as field programmable gate arrays  ... 
doi:10.1109/cvprw.2010.5543769 dblp:conf/cvpr/HumenbergerEK10 fatcat:a47d4gz6xrc3vnokq55trhodfq

Real-time registration of video with ultrasound using stereo disparity

Jihang Wang, Samantha Horvath, George Stetten, Mel Siegel, John Galeotti, David R. Holmes III, Kenneth H. Wong
2012 Medical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling  
This report proposes an image fusion device called Probe-Sight to realize the above functionality by mounting two video cameras on an ultrasound probe in a lightweight aluminum frame. iv  ...  visualization technique, in general, are the capabilities to accurately acquire the 3D point clouds of the exterior surface along with high resolution ultrasound data and then to register them properly into one  ...  ProbeSight's real-time stereo vision algorithm and real-time rendering technique allow for interactive use.  ... 
doi:10.1117/12.911222 dblp:conf/miigp/WangHSSG12 fatcat:a7ufifz6y5byvdxmaoxraefjdq

ReS2tAC—UAV-Borne Real-Time SGM Stereo Optimized for Embedded ARM and CUDA Devices

Boitumelo Ruf, Jonas Mohrs, Martin Weinmann, Stefan Hinz, Jürgen Beyerer
2021 Sensors  
With this in mind, we propose an approach for real-time embedded stereo processing on ARM and CUDA-enabled devices, which is based on the popular and widely used Semi-Global Matching algorithm.  ...  graphics hardware.  ...  Acknowledgments: We would like to thank Raphael Senk and Shreyas Manjunath for their support in setting up and using the UAV with the on-board processing unit.  ... 
doi:10.3390/s21113938 fatcat:f4lwpg3bozf7fmkrqcrjiwffua

Real-time stereo matching on CUDA using Fourier descriptors and dynamic programming

Mohamed Hallek, Fethi Smach, Mohamed Atri
2019 Computational Visual Media  
Our stereo matching algorithm is evaluated using the Middlebury stereo benchmark; our approach has been implemented on parallel high-performance graphics hardware using CUDA to accelerate our algorithm  ...  , giving a real-time implementation.  ...  Different architectures are used to achieve real-time performance. One is based on field-programmable gate arrays (FPGAs) [19] .  ... 
doi:10.1007/s41095-019-0133-4 fatcat:bn3cijkebbecthrezqcihhgsbm

Real-Time Stereo Matching on CUDA Using an Iterative Refinement Method for Adaptive Support-Weight Correspondences

Jędrzej Kowalczuk, Eric T. Psota, Lance C. Perez
2013 IEEE transactions on circuits and systems for video technology (Print)  
High-quality real-time stereo matching has the potential to enable various computer vision applications including semi-automated robotic surgery, tele-immersion, and threedimensional video surveillance  ...  This method has been implemented on massively parallel high-performance graphics hardware using the CUDA computing engine.  ...  BACKGROUND Recently, the availability of massively parallel graphics hardware has enabled the development of real-time highresolution stereo matching.  ... 
doi:10.1109/tcsvt.2012.2203200 fatcat:wmb5bynbqjfkfc6usyr5dk4w4m

Stereo Correspondence Estimation by Two Dimensional Real Time Spiral Search Algorithm

2020 International Journal of Engineering and Advanced Technology  
This paper presents a new searching algorithm titled "Two Dimensional Real Time Spiral Search Algorithm (2DRTSSA)" to compute the stereo correspondence or dense disparity map of two rectified images.  ...  So the proposed method calculates stereo correspondence two dimensionally at a time and thus it increases the speed and accuracy over the existing state-of-the-arts methods of one dimensional and left-right  ...  Moreover, the 2DRTSSA algorithm does not require additional programmable 3D hardware like 3D Graphics Processing Unit (GPU).  ... 
doi:10.35940/ijeat.d8592.069520 fatcat:xozxjn3c3zbpdkwgdz4y7eh5du

Real-Time Underwater StereoFusion

Matija Rossi, Petar Trslić, Satja Sivčev, James Riordan, Daniel Toal, Gerard Dooly
2018 Sensors  
Unlike KinectFusion on which it is based, StereoFusion relies on a stereo camera as its main sensor.  ...  Many current and future applications of underwater robotics require real-time sensing and interpretation of the environment.  ...  Dense real-time 3D reconstruction is becoming feasible only recently, with the advent of widely available massively parallel commodity general purpose computing on graphics processing units (GPGPU).  ... 
doi:10.3390/s18113936 fatcat:djiaehdiqrfqhelzmartzdfcdy

Real-time stereo matching architecture based on 2D MRF model: a memory-efficient systolic array

Sungchan Park, Chao Chen, Hong Jeong, Sang Hyun Han
2011 EURASIP Journal on Image and Video Processing  
Our architecture records 19 times smaller memory than the global minimization technique, which is a principal step toward real-time chip implementation of the various iterative image processing algorithms  ...  We have realized it using the FPGA technology.  ...  Acknowledgements This work was supported by the following funds: the Brain Korea 21 project and the Ministry of Knowledge Economy, Korea, under the Core Technology Development for Breakthrough of Robot Vision  ... 
doi:10.1186/1687-5281-2011-4 fatcat:m2qojiricfg7nltfhux5krqy2e

Run-time Adaptation to Heterogeneous Processing Units for Real-time Stereo Vision

Benjamin Ranft, Oliver Denninger
2012 2012 IEEE 14th International Conference on High Performance Computing and Communication & 2012 IEEE 9th International Conference on Embedded Software and Systems  
To achieve real-time performance, we first utilize data element-parallelism individually on each processing unit.  ...  On this basis, we develop and implement further strategies for heterogeneous systems and automatic adaptation to the hardware available at run-time.  ...  Our implementations are able to meet real-time constraints and to compete with OpenCV, a widely-used and welloptimized computer vision library.  ... 
doi:10.1109/hpcc.2012.232 dblp:conf/hpcc/RanftD12 fatcat:ezz5rn7e3jb67nc247nujjruve
« Previous Showing results 1 — 15 out of 761 results