article

Real-time Visual Tracker by Stream Processing

Authors:

Oscar Mateo Lozano,

Kazuhiro OtsukaAuthors Info & Claims

Journal of Signal Processing Systems, Volume 57, Issue 2

Pages 285 - 295

https://doi.org/10.1007/s11265-008-0250-2

Published: 01 November 2009 Publication History

Abstract

In this work, we implement a real-time visual tracker that targets the position and 3D pose of objects in video sequences, specifically faces. The use of stream processors for the computations and efficient Sparse-Template-based particle filtering allows us to achieve real-time processing even when tracking multiple objects simultaneously in high-resolution video frames. Stream processing is a relatively new computing paradigm that permits the expression and execution of data-parallel algorithms with great efficiency and minimum effort. Using a GPU (graphics processing unit, a consumer-grade stream processor) and the NVIDIA CUDA technology, we can achieve performance improvements as large as ten times compared to a similar CPU-only tracker. At the same time, the Stream processing approach opens the door to other computing devices, like the Cell/BE or other multicore CPUs.

References

[1]

Otsuka, K., Yamato, J., Takemae, Y., & Murase, H. (2006). Conversation scene analysis with dynamic Bayesian network based on visual head tracking. In Proc. IEEE intl. conf. on multimedia and expo 2006 (pp. 949-952).

[2]

Doucet, A., Freitas, N., & Gordon (Eds.) (2001). Sequential Monte Carlo methods in practice . Springer.

[3]

Isard, M., & Blake, A. (1998). Condensation--conditional density propagation for visual tracking. In Proc. of the 6th intl. conf. on computer vision (pp. 107-112).

Digital Library

[4]

Owens, J. D., Luebke, D., Govindaraju, N., Harris, M., Krüger, J., Lefohn, A. E., et al. (2007). A survey of general-purpose computation on graphics hardware. Computer Graphics Forum, 26 (1), 80-113.

[5]

NVIDIA (2007). CUDA (compute unified device architecture) programming guide ver.1.0. http://developer.nvidia. com/object/cuda.html.

[6]

Peercy, M., Segal, M., & Gertsmann, D. (2006). A performance-oriented data parallel virtual machine for GPUs. In Proc. SIGGRAPH 2006 .

Digital Library

[7]

McCool, M. (2007). Multi-core cpus, accelerators, and the many-core future: A unified software approach with rapidmind. In Proc. SIGGRAPH 2007 .

[8]

Kapasi, U. J., Rixner, S., Dally, W. J., Khailany, B., Ahn, J. H., Mattson, P., et al. (2003). Programmable stream processors. IEEE Computer, 36 , 54-62, August.

Digital Library

[9]

Venkatasubramanian, S. (2003). The graphics card as a stream computer. In SIGMOD-DIMACS workshop on management and processing of data streams .

[10]

Kapasi, U., Dally,W. J., Rixner, S., Owens, J. D., & Khailany, B. (2002). The imagine stream processor. In Proc. of intl. conf. on computer design (pp. 282-288).

Digital Library

[11]

Khailany, B., Williams, T., Lin, J., Long, E., Rygh, M., Tovey, D., et al. (2007). A programmable 512 gops stream processor for signal, image, and video processing. In IEEE international solid-state circuits conference 2007 digest of technical papers (pp. 272-602).

[12]

Fung, J., & Mann, S. (2004). Computer vision signal processing on graphics processing units. In Proc. IEEE international conference on acoustics, speech, and signal processing (Vol. 5, pp. 93-96).

[13]

Montemayor, A. S., Pantrigo, J. J., Sánchez, Á., & Fernández, F. (2004). Particle filter on gpus for real-time tracking. In Proc. of ACM SIGGRAPH (p. 94).

Digital Library

[14]

Montemayor, A. S., Pantrigo, J. J., Cabido, R., & Payne, B. (2006). Bandwidth improved GPU particle filter for visual tracking. In Ibero-American symposyum on computer graphics--SIACG .

[15]

Arulampalam, S., Maskell, S., Gordon, N. J., & Clapp, T. (2002). A tutorial on particle filters for on-line nonlinear/ non-Gaussian Bayesian tracking. IEEE Transactions of Signal Processing, 50 (2), 174-188, February.

Digital Library

[16]

Matsubara, Y., & Shakunaga, T. (2005). Sparse template matching and its application to real-time object tracking. IPSJ Transactions on Computer Vision and Image Media, 46 (9), 17-40.

[17]

Matsubara, Y., & Shakunaga, T. (2004). Real-time object tracking by sparse template matching. In IPSJ SIG technical report, no. 26 (pp. 49-56).

[18]

Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proc. of the IEEE computer society conference on computer vision and pattern recognition (Vol. 1, pp. 511-518).

[19]

Viola, P., & Jones, M. (2004). Robust real-time face detection. International Journal of Computer Vision, 57 (2), 137-154.

Digital Library

[20]

Edwards, G. J., Taylor, C. J., & Cootes, T. F. (1998). Interpreting face images using active appearance models. In Proc. intl. conf. on face and gesture recognition (pp. 300-305).

Digital Library

[21]

Horn, D. (2005). Stream reduction operations for GPGPU applications. GPU Gems 2 . Addison Wesley.

[22]

Buck, I., Foley, T., Horn, D., Sugerman, J., Fatahalian, K., Houston, M., et al. (2004). Brook for GPUs: Stream computing on graphics hardware. ACM Transactions on Graphics, 23 (3), 777-786.

Digital Library

[23]

Stegmann, M. B., Ersbøll, B. K., & Larsen, R. (2003). Fame - a flexible appearance modelling environment. IEEE Transactions on Medical Imaging, 22 (10), 1319-1331.

[24]

Ahlberg, J. (2001). Candide-3 - an updated parameterized face. Technical report, Dept. of Electrical Engineering, Linköping University.

[25]

Bolic, M., Djuric, P. M., & Hong, S. (2005). Resampling algorithms and architectures for distributed particle filters. IEEE Transactions on Signal Processing, 53 (7), 2442-2450, July.

Digital Library

Cited By

Otsuka KKasuga KKöhler MD'Mello SGeorgiou PScherer SProvost ESoleymani MWorsley M(2018)Estimating Visual Focus of Attention in Multiparty Meetings using Deep Convolutional Neural NetworksProceedings of the 20th ACM International Conference on Multimodal Interaction10.1145/3242969.3242973(191-199)Online publication date: 2-Oct-2018
https://dl.acm.org/doi/10.1145/3242969.3242973
Chen ZLv GLv LFan TWang H(2018)Spectrum Analysis-Based Traffic Video SynopsisJournal of Signal Processing Systems10.1007/s11265-018-1345-z90:8-9(1257-1267)Online publication date: 1-Sep-2018
https://dl.acm.org/doi/10.1007/s11265-018-1345-z
Battistone FPetrosino ASantopietro V(2018)Watch OutJournal of Signal Processing Systems10.1007/s11265-017-1279-x90:6(891-900)Online publication date: 1-Jun-2018
https://dl.acm.org/doi/10.1007/s11265-017-1279-x
Show More Cited By

Real-time Visual Tracker by Stream Processing
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
      2. Computer vision tasks

Recommendations

A holistic approach to build real-time stream processing system with GPU

Stream processing needs to process huge volume of data with strict deadline requirements. These applications generally consume large amount of network bandwidth and involve compute-intensive operations. Accelerating such operations with general purpose ...
Design and implementation of stream processing system and library for CELL broadband engine processors
PDCS '07: Proceedings of the 19th IASTED International Conference on Parallel and Distributed Computing and Systems

To bring out high performance in applications running on a CELL Broadband Engine processor (CELL processor), developers have to know its architecture and have special skills of the programming. As we know, the CELL processor is suitable for stream ...
Stream Processing on Hybrid CPU/Intel^® Xeon Phi^™ Systems
Euro-Par 2018: Parallel Processing
Abstract
Stream processing is currently central to handle large volumes of data generated at high rates. However, the efficient processing of such quantity of data demands massively parallel hardware. The usual approach is to rely on clusters of multi-...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Journal of Signal Processing Systems

Journal of Signal Processing Systems Volume 57, Issue 2

November 2009

170 pages

ISSN:1939-8018

EISSN:1939-8115

Issue’s Table of Contents

Copyright © Copyright © 2009 Springer Science+Business Media, LLC.

Publisher

Kluwer Academic Publishers

United States

Publication History

Published: 01 November 2009

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

15
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 08 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Otsuka KKasuga KKöhler MD'Mello SGeorgiou PScherer SProvost ESoleymani MWorsley M(2018)Estimating Visual Focus of Attention in Multiparty Meetings using Deep Convolutional Neural NetworksProceedings of the 20th ACM International Conference on Multimodal Interaction10.1145/3242969.3242973(191-199)Online publication date: 2-Oct-2018
https://dl.acm.org/doi/10.1145/3242969.3242973
Chen ZLv GLv LFan TWang H(2018)Spectrum Analysis-Based Traffic Video SynopsisJournal of Signal Processing Systems10.1007/s11265-018-1345-z90:8-9(1257-1267)Online publication date: 1-Sep-2018
https://dl.acm.org/doi/10.1007/s11265-018-1345-z
Battistone FPetrosino ASantopietro V(2018)Watch OutJournal of Signal Processing Systems10.1007/s11265-017-1279-x90:6(891-900)Online publication date: 1-Jun-2018
https://dl.acm.org/doi/10.1007/s11265-017-1279-x
Jáuregui DHorain P(2017)Real-time 3D motion capture by monocular vision and virtual renderingMachine Vision and Applications10.1007/s00138-017-0861-328:8(839-858)Online publication date: 1-Nov-2017
https://dl.acm.org/doi/10.1007/s00138-017-0861-3
Míguez JVázquez M(2016)A proof of uniform convergence over time for a distributed particle filterSignal Processing10.1016/j.sigpro.2015.11.015122:C(152-163)Online publication date: 1-May-2016
https://dl.acm.org/doi/10.1016/j.sigpro.2015.11.015
Choi CChristensen H(2016)RGB-D object pose estimation in unstructured environmentsRobotics and Autonomous Systems10.1016/j.robot.2015.09.02075:PB(595-613)Online publication date: 1-Jan-2016
https://dl.acm.org/doi/10.1016/j.robot.2015.09.020
Palossi DRuggiero MBenini L(2015)3D CV Descriptor on Parallel Heterogeneous PlatformsACM Transactions on Embedded Computing Systems10.1145/273337714:4(1-25)Online publication date: 24-Sep-2015
https://dl.acm.org/doi/10.1145/2733377
Otsuka KKumano SIshii RZbogar MYamato JEpps JChen FOviatt SMase KSears AJokinen KSchuller B(2013)MM+SpaceProceedings of the 15th ACM on International conference on multimodal interaction10.1145/2522848.2522854(389-396)Online publication date: 9-Dec-2013
https://dl.acm.org/doi/10.1145/2522848.2522854
Yamamoto MNakagawa HEgawa KNagamatsu T(2013)Development of a mobile tablet PC with gaze-tracking functionProceedings of the 15th international conference on Human Interface and the Management of Information: information and interaction for health, safety, mobility and complex environments - Volume Part II10.1007/978-3-642-39215-3_49(421-429)Online publication date: 21-Jul-2013
https://dl.acm.org/doi/10.1007/978-3-642-39215-3_49
Otsuka KKumano SMikami DMatsuda MYamato JKonstan JChi EHöök K(2012)Reconstructing multiparty conversation field by augmenting human head motions via dynamic displaysCHI '12 Extended Abstracts on Human Factors in Computing Systems10.1145/2212776.2223783(2243-2248)Online publication date: 5-May-2012
https://dl.acm.org/doi/10.1145/2212776.2223783
Show More Cited By

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents