Abstract
To meet both flexibility and performance requirements, particularly when implementing high-end real-time image/video processing algorithms, the paper proposes to combine the application specific instruction-set processor (ASIP) paradigm with the reconfigurable hardware one. As case studies, the design of partially reconfigurable ASIP (r-ASIP) architectures is presented for two classes of algorithms with widespread diffusion in image/video processing: motion estimation and retinex filtering. Design optimizations are addressed at both algorithmic and architectural levels. Special processor concepts used to trade-off performance versus flexibility and to enable new features of post-fabrication configurability are shown. Silicon implementation results are compared to known ASIC, DSP or reconfigurable designs; the proposed r-ASIPs stand for their better performance–flexibility figures in the respective algorithmic class.
Similar content being viewed by others
Notes
PSNR and bit-rate results in Table 1 are obtained using the H.264 JM 10 software model with maximum search displacement 16, five reference frames, seven variable block sizes. Tests include static videos as Akiyo and dynamic ones as Stefan (a Tennis scene), Mobile and Tennis Table.
References
Peters, H., Sethuraman, R., Beric, A., Meuwissen, P., Balakrishnan, S., Pinto, C., Kruijtzer, W., Ernst, F., Alkadi, G., van Meerbergen, J., de Haan, G.: Application specific instruction-set processor template for motion estimation in video applications. IEEE Trans Circuits Syst Video Technol 15, 508–527 (2005)
Vogt, T., Wehn N.: A reconfigurable application specific instruction set processor for Viterbi and Log-MAP decoding. IEEE Workshop Signal Proc Syst Des Impl, pp. 142–147 (2006)
Dinoi, L., Martini, R., Masera, G., Quaglio, F., Vacca, F.: ASIP design for partially structured LDPC codes. Electron Lett 42(18), 49–50 (2006)
Momcilovic, S., et al.: Application specific instruction set processor for adaptive video motion estimation. In: Proceedings of IEEE Euromicro DSD 160–167 (2006)
Bajot, Y., Mehrez, H.: Customizable DSP architecture for ASIP core design. In: Proceedings of ISCAS’01, pp 302–305 (2001)
Kappen, G., Noll, T.: Application specific instruction processor based implementation of a GNSS receiver on an FPGA. IEEE DATE ’06, vol. 2, pp. 1–6 (2006)
Lee, J., Moon, J., Heo, K., Sunwoo, M., Oh, S., Kim, I.: Implementation of application-specific DSP for OFDM systems. In: Proceedings of IEEE Int Conf Circuits Syst (ISCAS), pp. 665–668 (2007)
Yue, H., Lai, M.-C., Dai, K., Wang, Z.-.Y.: Design of a configurable embedded processor architecture for DSP functions. In: Proceedings of IEEE ICPADS’05, pp. 27–31 (2005)
Chattopadhyay, A., Ahmed, W., Karuri, K., Kammler, D., Leupers, R., Ascheid, G., Meyr, H.: Design space exploration of partially reconfigurable embedded processors. In: IEEE DATE’07, pp. 1–6 (2007)
Schliebusch, O., Chattopadhyay, A., Witte. E.M., Kammler, D., Ascheid, G., Leupers, R., Meyr, H.: Optimization techniques for ADL-driven RTL processor synthesys. In: Proceedings of IEEE workshop on rapid prototyping systems, Montreal, pp. 165–171 (2005)
Schliebusch, O., Chattopadhyay, A., Kammler, D., Ascheid, G., Leupers, R., Meyr, H., Kogel, T.: A framework for automated and optimized ASIP implementation supporting multiple hardware description languages. IEEE ASP-DAC 2005 1:280–285 (2005)
Goossens, G., Lanneer, D., Geurts, W., Van Praet, J.: Design of ASIPs in multi-processor SoCs using the Chess/Checkers retargetable tool suite. In: IEEE International Symposium on System-on-Chip, pp. 1–4 (2006)
Todman, T., Constantinides, G., Wilton, S., Mencer, O., Luk, W., Cheung, P.: Reconfigurable computing: architectures and design methods. IEE Proc Comput Digit Tech 152(2), 193–207 (2005)
Compton, K., Hauck, S.: Reconfigurable computing: a survey of systems and software. ACM Comput Surv 2, 171–210 (2002)
Kuhn, P.: Algorithms, complexity analysis and VLSI architectures for MPEG–4 motion estimation. Kluwer, Dordrecht (1999)
Wiegand, T., Sullivan, G., Bjntegaard, G., Luthra, A.: Overview of the H.264/AVC video coding standard. IEEE Trans. Circuits. Syst. Video. Technol. 13(7):560–576 (2003)
Ostermann, J., et al.: Video coding with H.264/AVC: tools, performance and complexity. IEEE Circuits. Syst. Mag. 4 (1):7–28 (2004)
Huang, Y.W., Wang, T.-C., Hsieh, B.-Y., Chen, L.-G.: Hardware architecture design for variable block size motion estimation in MPEG–4 AVC/JVT/ITU-T H.264. In: Proceedings of IEEE ISCAS, Bangkok, pp. 796–799 (2003)
Saponara, S., Casula, M., Rovati, F., Alfonso, D., Fanucci, L.: Dynamic control of motion estimation search parameters for low complex H.264 video coding. IEEE Trans. Consum. Electron. 52(1):232–239 (2006)
De Vleeschouwer, C., et al.: Algorithmic and architectural co-design of a motion estimation engine for low-power video devices. IEEE Trans Circuits Syst Video Technol 12(12), 1093–1105 (2002)
Fanucci, L., Saponara, S., Bertini, L.: A parametric VLSI architecture for video motion estimation. Integr VLSI J 31(1), 79–100 (2001)
Chen Z., Xu J., He Y.: Efficient fast ME predictions and early termination strategy based on H.264 statistical characters. In: Proceedings of ICICS–PCM 2003, pp. 213–218 (2003)
Ogata, M., Tsuchiya, T., Kubozono, T., Ueda, K.: Dynamic range compression based on illumination compensation. IEEE Trans Consum Electron 47(3), 548–558 (2001)
Rahman Z., Jobson D., Woodell G., Hines G.: Impact of multiscale retinex computation on performance of segmentation algorithms. In: Proceedings of SPIE 5438: visual Information Processing XIII, pp. 171–182 (2004)
Jobson, D.J., Rahman, Z., Woodell, G.: A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Trans Image Process 6(7), 965–976 (1997)
Tao, L., Tompkins, R., Asari, V.K.: An illuminance-reflectance nonlinear video enhancement model for homeland security spplications. In: Proceedings of applied imagery and pattern Rec. Workshop, pp. 28–35 (2005)
Wang, H, Li, S.Z, Wang, Y, Zhang J.: Self quotient image for face recognition. In: Proceedings of IEEE ICIP 2004, pp. 1397–1400 (2004)
Iqbal, N.: Automatic enhancement of chest radiography using-Retinex processing. In: Proceedings of international multi topic conference (INMIC) 2002, December 27–28, pp. 27–31 (2002)
Funt, B., Ciurea, F., McCann, J.: Retinex in Matlab. J Electron Imaging 13(1), 48–57 (2004)
Saponara, S., Fanucci, L., Ramponi, G., Marsi, S.: Algorithmic and architectural design for real-time and power-efficient Retinex image/video processing. J Real Time Image Process 1(4), 267–283 (2007)
Hines, G., Rahman, Z., Jobson, D.J., Woodell G.A., Harrah S.D.: Real-time Enhanced Vision System, Proceedings of SPIE 5802: enhanced and synthetic vision 2005, pp. 127–134 (2005)
Saponara, S., et al.: Cost-effective VLSI design of non linear image processing filters, Proceedings of IEEE Euromicro DSD 2005, pp. 322–32 (2005)
Saponara, S., Fanucci, L., Ramponi, G., Marsi, S., Kammler, D., Witte, E.: Application-specific instruction-set processor for Retinex-like image and video processing. IEEE Trans Circuit Syst II 54(7), 596–600 (2007)
Xilinx, Power PC405 processor reference guide (2003)
Altera, NIOS II processor reference handbook (2004)
Paolucci P.S., Jerraya A., Leupers R., Thiele L., Vicini P., “SHAPES: a tiled scalable software hardware architecture platform for embedded systems”, Proceedings of IEEE CODES 2006, pp. 167–172 (2006)
Singh, H., Lee, M., Lu, G., Kurdahi, F., Bagherzadeh, N., Chaves, E.: MorphoSys: a integrated reconfigurable system for data parallel and compute intensive applications. IEEE Trans Comput 49(5), 465–481 (2000)
Acknowledgments
Discussions with Prof. G. Ramponi and Prof. S. Marsi, University of Trieste and Dr. D. Kammler and Dr. E. Witte, RWTH Aachen University, are gratefully acknowledged. The work has been partially supported by the European 6th FP Network of Excellence “Newcom” and the Integrated project “SHAPES”.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Saponara, S., Casula, M. & Fanucci, L. ASIP-based reconfigurable architectures for power-efficient and real-time image/video processing. J Real-Time Image Proc 3, 201–216 (2008). https://doi.org/10.1007/s11554-008-0084-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-008-0084-y