Parallelization and performance optimization of video feature extractions on multi-core systems

doi:10.7523/j.issn.2095-6134.2011.4.015

Abstract

Abstract:

The low-level video feature extractions are the most time-consuming components in content-based video information retrieval systems. In this paper we study parallelization and performance optimization methods of four video feature extractions on multi-core systems. Experiments show that the processing speeds of these programs are 17 times the original processing speed on average when eight cores are used. Besides, detailed performance analysis helps us find bottlenecks and suggest ways to further improve multi-core systems performance in future.

Key words: program performance optimization, multi-core systems, video feature extraction

CLC Number:

TP311

ZHANG Qi, CHEN Yu-Rong, LI Jian-Guo, HU Yun, XU Yin-Long. Parallelization and performance optimization of video feature extractions on multi-core systems[J]. , 2011, 28(4): 531-547.

References

[1] Michael S L, Nicu S, Chabane D, et al. Content-based multimedia information retrieval: state of the art and challenges
[J]. ACM Transactions on Multimedia Computing, Communications and Applications, 2006, 2(1):1-19.

[2] Martinez J M. MPEG-7 overview:technical report . N6828 ISO/IEC/JTC1/SC29/WG11, 2004.

[3] Cao J, Lan Y, Li J, et al. Intelligent multimedia group of Tsinghua University ad TRECVID 2006 // Proceedings of TRECVID’06. 2006.

[4] Intel^®. Multi-core technology . . http://www.intel.com/multi-core/.

[5] Zhang Q, Chen Y, Li J, et al. Parallelization and performance analysis of video feature extractions on multi-core based systems // Proceedings of the 36th International Conference on Parallel Processing. Xi’an, China, 2007.

[6] Zhang Q, Chen Y, Zhang Y, et al. SIFT implementation and optimization for multi-core systems // Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium. Miami, Florida, United States, 2008.

[7] Feng H, Li E, Chen Y, et al. Parallelization and characterization of SIFT on multi-core systems // Proceedings of IEEE International Symposium on Workload Characterization, 2008. Seattle, USA, 2008.

[8] Miao Q, Chen Y, Li J, et al. Parallelization and optimization of a CBVIR system on multi-core architectures // Proceedings of the 23rd IEEE International Parallel and Distributed Processing Symposium. Rome, Italy, 2009.

[9] Li E, Li W, Tong X, et al. Accelerating video-mining applications using many small, general-purpose cores
[J]. IEEE Micro, 2008, 28(5):8-21.

[10] Li W, Tong X, Wang T, et al. Parallelization strategies and performance analysis of media mining applications on multi-core processors
[J]. Journal of Signal Processing Systems, 2009, 57(2):213-228.

[11] Hong C, Chen W, Zheng W, et al. Parallelization and characterization of probabilistic latent semantic analysis // Proceedings of the 37th International Conference on Parallel Processing. 2008:628- 635.

[12] Snavely A, Tullsen D M, Voelker G. Symbiotic jobscheduling with priorities for a simultaneous multithreading processor // Proceedings of the SIGMETRICS’02. 2002:66-76.

[13] Fedorova A, Seltzer M, Small C, et al. Performance of multithreaded chip multiprocessors and implications for operating system design // Proceedings of the USENIX’05. 2005:26.

[14] Fedorova A, Seltzer M, Smith M D. Improving performance isolation on chip multiprocessors via an operating system scheduler // Proceedings of the PACT’07. 2007:25-38.

[15] Chen S, Gibbons P B, Kozuch M, et al. Scheduling threads for constructive cache sharing on CMPs // Proceedings of the SPAA’07. 2007:105-115.

[16] Lee R, Ding X, Chen F, et al. MCC-DB: Minimizing cache conflicts in multi-core processors for databases // Proceedings of the VLDB’09. 2009.

[17] Sutter H. The free lunch is over: A fundamental turn toward concurrency in software
[J]. Dr Dobb’s Journal, 2005, 30(3).

[18] Huang J, Kumar S R, Mitra M, et al. Spatial color indexing and applications
[J]. International Journal of Computer Vision, 1999, 35(3):245-268.

[19] Mao J, Jain A K. Texture classification and segmentation using multi-resolution simultaneous autoregressive models
[J]. Pattern Recognition, 1992, 25(2):173-188.

[20] Manjunath B S, Ma W Y. Texture features for browsing and retrieval of image data
[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(8):837-842.

[21] Lowe D G. Distinctive image features from scale-invariant keypoints
[J]. International Journal of Computer Vision, 2004, 60(2):91-110.

[22] Ma W Y, Zhang H J. Benchmarking of image features for content-based retrieval // Conference Record of the 32nd Asilomar Conference on Signals, Systems & Computers. Pacific Grove, CA, 1998:253-257.

[23] Xu K, Georgescu B, Comaniciu D, et al. Performance analysis in content-based retrieval with textures // Proceedings of the 15th International Conference on Pattern Recognition. 2000:4275-4279.

[24] Campbell M, Ebadollahi S, Naphade M, et al. IBM research TRECVID-2006 Video retrieval system // Proceedings of TRECVID’06. 2006.

[25] Lee T S. Image representation using 2D Gabor wavelets
[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(10):959-971.

[26] Estrada F, Jepson A, Fleet D. Local features tutorial: technique report . (2004) . http://www.cs.toronto.edu/~jepson/csc2503/tutSIFT04.pdf.

[27] Intel Corporation. Intel^®. VTune^TM performance analyzer . . http://www.intel.com/software/products/vtune/.

[28] Matteo F, Steven G J. The design and implementation of FFTW3 //Proceedings of the IEEE, 2005, 93(2): 216-231.

[29] Intel Corporation. Intel^®. Math kernel library . http://www.intel.com/software/products/mkl/.

[30] Intel Corporation. Intel^®. 64 and IA-32 architectures optimization reference manual
[M]. CA, USA: Intel Corporation, 2006.

[31] Hugher C J, Grzeszczuk R, Sifakis E, et al. Physical simulation for animation and visual effects: parallelization and characterization for chip multiprocessors // Proceedings of the 34th Annual International Symposium on Computer Architecture. 2007.

[32] The OpenMP Architecture Review Board. OpenMP C and C+ + application program interface Ver 2.0 .(2002-03) .http://www.openmp.org/mp-documents/cspec20.pdf.

[33] Intel^®. Thread checker . . http://software.intel.com/en-us/intel-thread-checker/

[34] Salehi J D, Kurose J F, Towsley D F. The effectiveness of affinity-based scheduling in multiprocessor network protocol processing
[J]. IEEE/ACM Transactions on Networking, 1996, 4(4):516-530.