High performance motion detection: Some trends toward new embedded architectures for vision systems

Journal of Real-Time Image Processing

Volumn 4, Issue 2, 2009, Pages 127-146

  Lacassagne, Lionel ^a   Manzanera, Antoine ^b   Denoulet, Julien ^c   Mérigot, Alain ^a  

^a UNIVERSITÉ PARIS SACLAY   (France)

^b ENSTA PARISTECH   (France)

^c SORBONNE UNIVERSITÉ   (France)

Author keywords

Associative nets model; Embedded system; High performance computing; Image processing; Motion detection; Parallel architecture; Programmable artificial retina; RISC; SIMD; SWAR; Vision; Vision SoC

Indexed keywords

ASSOCIATIVE PROCESSING; IMAGE PROCESSING; MOTION ANALYSIS; PARALLEL ARCHITECTURES; REDUCED INSTRUCTION SET COMPUTING; SYSTEM-ON-CHIP; VISION;

ARTIFICIAL RETINAS; ASSOCIATIVE NETS MODEL; HIGH PERFORMANCE COMPUTING; MOTION DETECTION; SIMD; SWAR; VISION SOC;

EMBEDDED SYSTEMS;

EID: 67349226371     PISSN: 18618200     EISSN: None     Source Type: Journal    
DOI: 10.1007/s11554-008-0096-7     Document Type: Article

References (42)

1. Azencott, R.: Simulated Annealing: Parallelization Techniques. Wiley, New York (1992)
2. Bellon, A., Derutin, J.-P., Heitz, F., Ricquebourg, Y.: Real-time collision avoidance at road-crossings on board the Prometheus-ProLab 2 vehicle. Intell Vehicles, pp. 56-61 (1994)
3. Biancardi, A., Segrovia-Martinez, M.: Adaptative segmentation of MR axial brain images using connected components. In: International Workshop on Visual Form, Capri, pp. 295-302 (2001)
4. P Bouthémy P Lalande 1993 Recovery of moving object in an image sequence using local spatiotemporal contextual information Opt Eng 32 6 1205 1212
5. Blelloch, G.: Vector Models for Data-Parallel Computing. MIT Press, Cambridge (1990)
6. BrookGPU: http://ati.amd.com/technology/streamcomputing
7. Caplier, A., Bonnaud, L., Chassery, J.-M.: Robust fast extraction of video objects combining frame differences and adaptive reference image. Int Conf Image Process, pp. 785-788 (2001)
8. M. Ceccarelli A. Petrosino 2002 A parallel fuzzy scale-space approach to the unsupervised texture separation Pattern Recognit Lett 23 5 557 567 (Pubitemid 34262286)
9. F.S. Cohen D.B. Cooper 1987 Simple parallel hierarchical and relaxation algorithms for segmenting non-causal Markovian random fields IEEE PAMI 9 2 195 219 (Pubitemid 17565877)
10. Cray X1: http://www.cray.com/products/x1/specifications.html
11. CUDA: http://www.nvidia.com/cuda
12. Denoulet, J., Mérigot, A.: System on chip evolution of a SIMD architecture for image processing. In: Computer Architecture and Machine Perception, New Orleans, 12-16 May 2003. doi: 10.1109/CAMP.2003.1598175
13. Denoulet, J., Mérigot, A.: Evaluation of a SIMD architecture dedicated to image processing. Global Signal Process (2004)
14. Denoulet, J., Mostafaoui, G., Lacassagne, L., Mérigot, A.: Implementing motion Markov detection on General Purpose Processor and Associative Mesh. In: Computer Architecture and Machine Perception, Palermo, pp 288-293 (2005)
15. Diefendorff, K., Dubeyn, P.K., Hochsprung, R., Scales, H.: Altivec extension to PowerPC accelerates media processing. In: IEEE Micro (2000)
16. Ducourthial, B., Merigot, A.: Parallel asynchronous computations for image analysis. Proc IEEE 90(7), 1218-1229 (2002)
17. Ducourthial, B., Constantinescu, G., Merigot, A.: Implementing image analysis with a graph-based parallel computing model. Computing. In: Supplementum, GbR'97, Workshop on Graph based Representation, Lyon, pp. 111-121 (1997)
18. P. Dudek 2006 An asynchronous cellular logic network for trigger-wave image processing on fine-grain massively parralel arrays IEEE Trans Circuits Syst II Express Briefs 53 5 354 358 (Pubitemid 43786577)
19. Dulac, D., Merigot, A., Mohammadi, S.: Associative meshes: a new parallel architecture for image analysis applications. In: Computer Architecture and Machine Perception, News Orleans, pp 393-399, 15-17 December 1993
20. R. Forchheimer A. Astrøm 1994 Near-sensor image processing: a new paradigm IEEE Trans Image Process 3 736 746
21. W. Daniel Hillis L.W. Tucker 1993 The CM-5 connection machine: a scalable supercomputer Commun ACM 36 11 31 40
22. B. Galilee F. Mamalet M. Renaudin P.Y. Coulon 2007 Parallel asynchronous watershed algorithm-architecture IEEE Trans Parallel Distrib Syst 18 1 44 56
23. Gies V., Bernard T.: Increasing interconnection network connectivity for reducing operator complexity in asynchronous vision systems. In: International Conference on Discrete Geometry for Computer Imagery, Poitiers, pp.1-10 (2005)
24. Gies, V., Bernard, T.M.: Tree extension of micro-pipelines for mixed synchronous-asynchronous implementation of regional image computations. In: Proceedings of SPIE, vol 5677, Sensors and Camera Systems for Scientific and Industrial Applications VI, SPIE (2005)
25. Klein, J.-C., Lemonnier, F., Gauthier, M., Peyrard, R.: Hardware implementation of the watershed zone algorithm based on a hierarchical queue structure. In: IEEE Workshop on Nonlinear Signal and Image Processing, Neos Marmaras (1995)
26. T. Komuro I. Ishii M. Ishikawa A. Yoshida 2003 A digital vision chip specialized for high-speed target tracking IEEE Trans Electron Devices 50 1 191 199
27. Lacassagne, L., Milgram, M., Garda, P.: Motion detection, labeling, data association and tracking, in real-time on RISC computer. In: International Conference on Image Analysis and Processing, Venise, pp 520-525 (1999)
28. P. Lalande P. Bouthemy 1990 A statistical approach to the detection and tracking of moving objects in an image sequence Eur Signal Process Conf 2 947 950
29. C. Limousin J. Sebot A. Vartanian N. Drach 2005 Architecture optimization for multimedia application exploiting data and thread-level parallelism J Syst Arch EUROMICRO J 51 1 15 27
30. Lohier, F., Lacassagne, L., Garda, P.: A New Methodology to Optimize DMA Data Caching: Application toward the Real-time Execution of an MRF-based Motion Detection Algorithm on a multi-processor DSP. International Conference on Signal Processing Applications and Technology, March 1999, Phoenix USA
31. Manzanera, A., Richefeu, J.: A robust and computationally efficient motion detection algorithm based on Sigma-Delta background estimation. In: Proceedings Indian Conference on Computer Vision, Graphics and Image Processing, Kolkata (2004)
32. A. Manzanera J. Richefeu 2007 A new motion detection algorithm based on Sigma-Delta background estimation Pattern Recognit Lett 28 3 320 328
33. A. Mérigot 1997 Associative nets model: a graph based parallel computing model IEEE Trans Comput 46 5 558 571 (Pubitemid 127761917)
34. A Mérigot B Zavidovique 2002 Image analysis on massively parallel computers: an architectural point of view Int J Pattern Recognit Image Anal 6 3 387 399
35. Nadrag, P., Manzanera, A., Burrus, N.: Smart retina as a contour-based visual interface. In: ACM Distributed Smart Cameras Workshop, DSC'06, Boulder (2006)
36. Sébot, J., Drach-Temam, N.: Memory bandwidth: the true bottleneck of SIMD multimedia performance on a superscalar processor. In: Proceedings of the 5th International Euro-Par Conference on Parallel Processing, pp 439-447, Springer, Berlin (2001)
37. Piskorski, S., Lacassagne, L., Bouaziz, S., Etiemble, D.: Customizing CPU instructions for embedded vision systems. IEEE Comput Arch Mach Percept Sensors (2006)
38. Piskorski, S. , Lacassagne, L., Kieffer, M., Etiemble, D.: Efficient floating point interval processing for embedded systems and applications. Int Symp Sci Comput Comput Arithmetic Valid Numer (2006)
39. List of reconfigurable architectures http://www.site.uottawa.ca/ ~rabielmo/personal/rc.html
40. A. Rodriguez-Vazquez G. Linan-Cembrano L. Carranza E. Roca-Moreno R. Carmona-Galan F. Jimenez-Garrido R. Dominguez-Castro S. Espejo Meana 2004 ACE16k: the third generation of mixed-signal SIMD-CNN ACE chips toward VSoCs IEEE Trans Circuits Syst 51 5 851 863
41. Intel Tera-scale project: http://techresearch.intel.com/articles/Tera- Scale/1449.htm
42. Zavidovique, B., Stamon, G.: Bilevel processing of multilevel images. In: Proceedings PRIP'81, Dallas (1981)