A PC-based real-time stereo vision system

• Autorzy: Di Stefano L. , Marchionni M. , Mattoccia S.
• Języki publikacji: EN

Abstrakty

EN

This paper describes a stereo vision system that enables real-time dense depthmeasurements on a personal computer. The system relies on a very efficient stereo matching engine that, unlike many other approaches which use two distinct matching phases in order to detect unreliable matches, uses a single matching phase. Our matching engine allows for rejecting most unreliable matches by exploiting violations of the uniqueness constraint as well as analysing behaviour of correlation scores. Real-time capability has been achieved by deploying very efficient incremental calculation schemes aimed at avoiding redundant calculations and parallelising the computationally expensive portion of the code with Single Instruction Multiple Data (SIMD) parallel instructions, available nowadays on almost any state-of-the-art general purpose microprocessors. Experimental results on real stereo sequences and preliminary results concerning a 3D people tracking/counting application show the effectiveness of the proposed PC-based stereo vision system for real-time applications.

Słowa kluczowe

EN

stereo; real-time; dense depth map; 3D; SIMD

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2004
• Tom: Vol. 13, No. 3
• Strony: 197--220
• Opis fizyczny: Bibliogr. 48 poz., il.

Twórcy

autor

Di Stefano L.

• Department of Electronics Computer Science and Systems (DEIS), Viale Risorgimento 2, 40136 Bologna, Italy

autor

Marchionni M.

• Department of Electronics Computer Science and Systems (DEIS), Viale Risorgimento 2, 40136 Bologna, Italy

autor

Mattoccia S.

• Department of Electronics Computer Science and Systems (DEIS), Viale Risorgimento 2, 40136 Bologna, Italy

Bibliografia

• [1] Fua P. Combining stereo and monocular information to compute dense depth maps that preserve depth discontinuities. 12th. Int. Joint Conf. on Artificial Intelligence, Sydney, Australia, 1292-1298, 1991.
• [2] Faugeras O., Hotz B., Mathieu H., Viville T., Zhang Z., Fua P., Thron E., Moll L., Berry G. Vuillemin J., Bertin P. and Proy C. Real-time correlation-based stereo: Algorithm, Implementation and Applications. INRIA Technical Report n. 2013, 1993.
• [3] Zabih R., Woodfill J. Non-parametric local transforms for computing visual correspondence. European Conf. on Computer Vision, Stockholm, Sweden, 151-158, 1994.
• [4] Fleet D.J.: Disparity from local weighted phase-correlation. Int. Conf. on Systems, Man, and Cybernetics, San Antonio, USA, Vol. 1, 48-54, 1994.
• [5] Kanade T., Kato H., Kimura S., Yoshida A., Oda K.: Development of a video-rate stereo machine. Int. Robotics and Systems Conf., (3), 95-100, 1995.
• [6] Robert L., Buffa M., Hebert M.: Weakly-calibrated stereo perception for rover navigation. Fifth Int. Conf. on Computer Vision, 1995.
• [7] Lee R. B.: Subword parallelism with MAX-2. IEEE Micro, 16(4), 51-59, 1996.
• [8] Peleg A., Weiser U.: MMX technology extension to the intel architecture. IEEE Micro, 16(4), 42-50, 1996.
• [9] Tremblay M., O'Connor M., Narayanan V., He L.: VIS speeds new media processing. IEEE Micro, 16(4), 10-20, 1996.
• [10] Sun C.: A fast stereo matching method. Digital Image Computing: Techniques and Applications, Auckland, New Zealand, 95-97, 1997.
• [11] Konolige K. Small vision systems: hardware and implementation. 8th Int. Symp. on Robotics Research, Hayama, Japan, 111-116, 1997.
• [12] Ruby B. Lee: Multimedia extensions for general-purpose processors. IEEE Workshop on Signal Processing Systems Design and Implementation, Leicester, United Kingdom, 9-23, 1997.
• [13] Woodfill J., Von Herzen B.: Real-Time Stereo Vision on the PARTS Reconfigurable Computer. IEEE Symp. on FPGAS for Custom Computing Machines, Napa Valley, USA, 201-209, 1997.
• [14] Trucco E., Verri A.: Introductory Techniques for 3-D Computer Vision. Prentice Hall, 1998.
• [15] Gluckman J., Nayar S.K., Thorek K.J.: Real-Time Omnidirectional and Panoramic Stereo. DARPA Image Understanding Workshop, Monterey, USA, 299-303, 1998.
• [16] Corke P., Dunn P., Banks J. Frame-rate stereopsis using non-parametric transforms and programmable logic, IEEE Int. Conf. on Robotics and Automation, Detroit, USA, 1999, 1928-1933.
• [17] Kimura S., Shinbo T., Yamaguchi H., Kawamura E., Naka K. A Convolver-Based Real-Time Stereo Machine (SAZAN). Conf. on Computer Vision and Pattern Recognition, 457-463, 1999.
• [18] Oberman S., Favor G., Weber F.: AMD 3DNow! Technology: Architecture and Implementations IEEE Micro, 19(2), 1999, 37-48.
• [19] Birchfield S., Tomasi C. Depth Discontinuities by Pixel-to-Pixel Stereo, Int. Journal of Comp Vision, 35(3), 1999, 269-293.
• [20] Diefendorff K., Dubey P.K., Hochsprung R., Scale H. VIS Speeds New Media Processing, IEEE Micro, 20(2), 2000, 85-95.
• [21] Egnal G. and Wildes R. Detecting binocular half-occlusions: empirical comparisons of four approaches, Int. Conf. on Computer Vision and Pattern Recognition, 2000, (2), 466-473.
• [22] Fusiello A., Roberto V. and Trucco E. Symmetric Stereo with Multiple Windowing, Int. Journa of Pattern Recognition and Artificial Intelligence, 14(8), 2000, 1053-1066.
• [23] Fusiello A., Trucco E. and Verri A. A compact algorithm for rectification of stereo pairs, Machine Vision and Applications, 12(1), 2000, 16-22.
• [24] Sharangpani H., Arora K. Itanium Processor Microarchitecture, IEEE Micro, 20(5), 2000, 24-43.
• [25] Shreekant T. and Huff T. Implementing streaming SIMD extensions on the Pentium III processor, IEEE Micro, 20(4), 2000, 47-57.
• [26] Van der Val G., Hansen M. and Piacentino M. The ACADIA Vision Processor, 5th Int. Workshop on Computer Architecture for Machine Perception, Padova, Italy, 2001, 31-40.
• [27] Tanahashi H., Yamamoto K., Caihua Wang, Niwa Y. Development of a stereo omnidirectional imaging system (SOS), IEEE Int. Conference on Industrial Electronics, Control and Instrumentation, Nagoya, Japan, 289-294, 2000.
• [28] Kolmogorov V. and Zabih R. Computing Visual Correspondence with Occlusions using Graph Cuts, Int. Conf. on Computer Vision, 2001, 508-515, 2001.
• [29] Di Stefano L., Marchionni M., Mattoccia S. and Neri G. A Fast Area-Based Stereo Matching Algorithm, 15th IAPR/CIPPRS Int. Conf. on Vision Interface, Calgary, Canada, 2002.
• [30] Di Stefano L. and Mattoccia S. Real-Time Stereo within the VIDET Project, Real Time Imaging, 8(5), 2002, 439-453.
• [31] Scharstein D. and Szeliski R. A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms,, Int. Journal of Computer Vision, 47(1-3), 2002, 7-42.
• [32] Muhlmann K., Maier D., Hesser J. and Manner R. Calculating Dense Disparity Maps from Color Stereo Images, an Efficient Implementation, Int. Journal of Computer Vision, 47(1-3), 2002, 79-88.
• [33] Hirschmuller H., Innocent P. and Garibaldi J. Real-Time Correlation-Based Stereo Vision with Reduced Border Errors, Int. Journal of Computer Vision, 47(1-3), 2002, 229-246.
• [34] Okutomi M., Katayama Y. and Oka S. A Simple Stereo Algorithm to Recover Precise Object Boundaries and Smooth Surfaces, Int. Journal of Computer Vision, 47(1-3), 2002, 261-273.
• [35] Di Stefano L., Mattoccia S. and Mola M. A Change Detection Algorithm based on Structure and Colour, IEEE Int. Conf. on Advanced Video and Signal Based Surveillance, Miami, USA, 252-259, 2003.
• [36] Jia Y., Xu Y., Liu W., Yang C., Zhu Y., Zhang X., An L.: A Miniature Stereo Vision Machine for Real-Time Dense Depth Mapping. 3th Int. Conf. Computer Vision Systems, Graz, Austria, 268-277, 2003.
• [37] Darabiha A., Rose J., Maclean J.W. Video-rate stereo depth measurement on programmable hardware. Int. Conf. on Computer Vision and Pattern Recognition, Madison, Wisconsin, Vol. 1, 203-210, 2003.
• [38] Jia Y., Xu Y., Liu W., Yang C., Zhu Y., Zhang X., An L.: A Miniature Stereo Vision Machine (MSVM-III) for Dense Disparity Mapping, 17th Int. Conf. on Pattern Recognition, Cambridge, UK, Vol. 1, 728-731, 2004.
• [39] Advanced RISC Machines, www.arm.com
• [40] Bouguet J.Y.Camera Calibration Toolbox, www.vision.caltech.edu/bouguetj/calib_doc/, 2004.
• [41] Di Stefano L., Marchionni M., Mattoccia S. Experimental results, www.vision.deis.unibo.it/"smattoccia/stereo.htm, 2004.
• [42] Harville M.Stereo person tracking with adaptive plan-view templates of height and occupancy statistics, Image and Vision Computing, 22(2), 127-142, 2004.
• [43] Point Grey Research, www.ptgrey.com
• [44] Videre Design, www.videredesign.com
• [45] Tyzx, www.tyzx.com
• [46] Open Source Computer Vision Library, http://www.intel.com/research/mrl/research/opencv/
• [47] Middlebury Stereo Vision Page www.middlebury.edu/stereo
• [48] Sunyoto H., van der Mark W., Gavrila D. M. A Comparative Study of Fast Dense Stereo Vision Algorithms, IEEE Intelligent Vehicles Symposium, Parma, Italy, 252-259, 2004.