Stereo Vision and Applications

December 2012

We have completed the design of our embedded (stereo and mono) camera with highly efficient FPGA onboard processing. In stereo mode, the whole processing pipeline fits into entry level FPGA devices without additional hardware requirements delivering accurate and dense depth map in real-time. The imaging sensors, connected to the FPGA board with a standard interface,  provide color and monochrome images up to 60 fps.
 The embedded camera has software API for:

    - Windows 32 and 64 bit 
    - Linux 32 and 64 bit
    - Linux ARM 
    - Mac  
    - Android 

Further details and videos will be available soon.

If you are interested in this project for your applications feel free to contact me:

This page provides an overview of the research activity concerned with stereo vision and aimed at developing:

• Accurate and fast algorithms for dense stereo correspondence
  
  
• Accurate 3D sensing based on FPGAs and embedded devices 
  
  • the first prototype of a custom designed stereo camera with real-time FPGA-based onboard processing is ready and under testing
    
    
• Computer vision applications that rely on dense depth measurements (e.g. 3D people tracking and counting, 3D change detection, etc)
  
  
• Accurate range sensing and fusion of 3D sensors data 

If you are interested in stereo vision, you might find interesting this recent seminar (updated Feb 17, 2012):

   
    Stefano Mattoccia
    "Stereo vision: algorithms and applications" []
    Università di Firenze, May 2012
 
    



If you have any questions feel free to contact me:
Stefano Mattoccia at: 

If you are looking for rectified stereo sequences follow this link.

• Locally consistent ToF and Stereo data fusion (CDC4CV 2012)
  
  C. Dal Mutto, P. Zanuttigh, S. Mattoccia, G. Cortelazzo, "Locally Consistent ToF and Stereo Data Fusion", 
  2nd Workshop on Consumer Depth Cameras for Computer Vision (CDC4CV2012), ECCV2012 Workshop, October 12, Firenze, Italy [Pdf] [Supplementary Material] [Bibtex] [Results]
  
  
  
• Stereo vision and scene segmentation (3DIMPVT 2011)
  
  C. Dal Mutto, P. Zanuttigh, G. M. Cortelazzo, S. Mattoccia, "Scene segmentation assisted by stereo vision",
  First joint 3DIM/3DPVT Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT 2011), May 16-19, 2011, Hangzhou, China [Pdf] [Bibtex]
  
  C. Dal Mutto, F. Dominio, P. Zanuttigh, S. Mattoccia, Book title: "Current advancements in stereo vision",
  Chapter "Stereo vision and scene segmentation", Edited by Asim Bhatti, July 2012, ISBN  978-953-51-0660-9, Publisher: I-Tech Education and Publishing Kirchengasse 43/3, A-1070, Vienna, Austria, [Table of contents] [Pdf]
  
  
  
• Linear Stereo Matching (ICCV 2011)
  
  L. De-Maeztu, S. Mattoccia, A. Villanueva, R. Cabeza, "Linear  stereo matching",
  International Conference on Computer Vision (ICCV 2011),  November 6-13, 2011, Barcelona, Spain [Pdf][Supplementary Material][Bibtex] 
  
  Additional experimental results concerned with this paper are available here
  
  
  
• A novel hetereogeneous framework for stereo matching (IPVC 2011)
  
  L. De-Maeztu, S. Mattoccia, A. Villanueva, R. Cabeza, "A novel heterogeneous framework for stereo matching",
  International Conference on Image Processing, Computer Vision and Pattern Recognition (IPVC2011), July 18-21, 2011, Las Vegas, USA [Pdf] [Bibtex]
  
  
  
  
• Near real-time Fast Bilateral Stereo on the GPU (ECVW 2011)
  
  Additional experimental results concerned with this paper are available here
  
  S. Mattoccia, M. Viti, F. Ries, "Near real-time Fast Bilateral Stereo on the GPU"
  7th IEEE Workshop on Embedded Computer Vision (ECVW20011), CVPR Workshop, June 20, 2011, Colorado Springs (CO), USA [Pdf] [Bibtex] Best Paper Award
  
  
  
  
• Accurate dense stereo by constraining local consistency on superpixels (ICPR 2010)
  
  
  
  Additional experimental results concerned with this paper are available here
  
  S. Mattoccia, "Accurate dense stereo by constraining local consistency on superpixels"
  20th International Conference on Pattern Recognition (ICPR2010), August 23-26, 2010, Istanbul, Turkey [Pdf] [Bibtex] 
  
  
  
  
• Fast locally consistent dense stereo on multicore (ECVW 2010)
  
  
  
  Additional experimental results concerned with this paper are available here
  
  S. Mattoccia, "Fast locally consistent dense stereo on multicore"
  Sixth IEEE Embedded Computer Vision Workshop (ECVW2010), CVPR workshop, June 13, 2010, San Francisco, USA [Pdf] [Supplemental][Bibtex]
  
  
  
  
• Improving the accuracy of fast dense stereo correspondence algorithms by enforcing local consistency of disparity fields (3DPVT 2010)
  
  
  
  Additional experimental results concerned with this paper are available here
  
  S. Mattoccia, "Improving the accuracy of fast dense stereo correspondence algorithms by enforcing local consistency of disparity fields"
  3D Data Processing, Visualization and Transmission (3DPVT2010), May 17-20, 2010, Paris, France [Pdf] [Supplemental][Bibtex]
  
  
  
  
• A locally global approach to stereo correspondence (3DIM 2009)
  
   
                          
  
  Additional experimental results concerned with the Locally Consistent (LC) approach proposed in this paper are available here
  Evaluation on the Middlebury dataset  (algorithm "LocallyConsistent") available here (link to evaluation)
  A comparison with state-of-the-art local approaches is available here
  
  
  S. Mattoccia, "A locally global approach to stereo correspondence"
  IEEE Workshop on 3D Digital Imaging and Modeling  (3DIM2009), October 3-4, 2009, Kyoto, Japan[Abstract][] [Bibtex]
  
  
  
  
  
• Accurate and efficient cost aggregation strategy for stereo correspondence based on approximated joint bilateral filtering (ACCV 2009)
  
   
        
  
  Additional experimental results concerned with the Fast Bilateral Stereo (FBS) algorithm are available here
  Evaluation on the Middlebury dataset  (algorithm "FastBilteral") available here (link to evaluation)
  A comparison with state-of-the-art local approaches is available here
  
  S. Mattoccia, S. Giardino, A. Gambini, "Accurate and efficient cost aggregation strategy for stereo correspondence based on approximated joint bilateral filtering"
  9th Asian Conference on Computer Vision (ACCV2009), September 23- 27, 2009,  Xi'an, China[][Bibtex] [Software, updated August 12th, 2010]
  
  
  
  
• Near real-time  stereo based on effective cost aggregation (ICPR 2008)
  
   
  
  Additional experimental results are available here
  Evaluation on the Middlebury [4] data set ("FastAggreg") is available here (link to evaluation)
  
  F. Tombari, S. Mattoccia, L. Di Stefano, E. Addimanda,“Near real-time stereo based on effective cost aggregation"
  International Conference on Pattern Recognition (ICPR 2008), December 8-11, 2008, Tampa, Florida, USA [] [Bibtex]
  
  
  
  
• Evaluation of cost aggregation strategies for dense stereo matching (CVPR 2008)
  
   
  
  Experimental (SAD, TAD, SSD, Original) are available here
  Software (Show Support) is available at the same location.
  
  F. Tombari,S. Mattoccia,L. Di Stefano, E. Addimanda, “Classification and evaluation of cost aggregation methods for stereo correspondence"
  IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2008), June 24-26, 2008, Anchorage, Alaska [] [Bibtex]
  
  
  
  
• Accurate stereo matching based on scanline optimization and adaptive support (ACCV2007)
  
         
  
  Preliminary results here
  Evaluation on the Middlebury dataset here (algorithm "SO+borders") available here (link to evaluation)
  
  S. Mattoccia, F. Tombari, L. Di Stefano,“Stereo vision enabling precise border localization within a scanline optimization framework"
  8th Asian Conference on Computer Vision (ACCV 2007), November 18-22, Tokyo, Japan [] [Bibtex]
  
  
  
  
• Segmentation-based adaptive support for accurate stereo correspondence (PSIVT2007)
  
   
  
  Experimental results available here
  Evaluation on the Middlebury dataset  (algorithm "Segment Support") available here (link to evaluation)
  
  F. Tombari, S. Mattoccia,L. Di Stefano, "Segmentation-based adaptive support for accurate stereo correspondence"
  IEEE Pacific-Rim Symposium on Image and Video Technology (PSIVT 2007), December 17-19, Santiago, Chile [] [Bibtex]
  
  
  
  
• Real-time stereo based on the uniqueness constraint (IVC 2004) and applications (3D people tracking/counting, 3D change detection)
  
  
  
  
  Experimental results and applications concerned with the Single Matching Phase (SMP) algorithm are availablehere
  In the same page you may find also rectified stereo sequences and disparity maps computed with the SMP algorithm.
  
  L. Di Stefano, M. Marchionni, S. Mattoccia, “A fast area-based stereo matching algorithm”
  Image and Vision Computing (IVC) 22(12), pp 983-1005, October 2004 [] [Bibtex]