Abstract
We present recent results of a performance benchmark of selected low-level vision algorithms implemented on different high-speed embedded platforms. The algorithms were implemented on a digital signal processor (DSP) (Texas Instruments TMS320C6414), a field-programmable gate array (FPGA) (Altera Stratix-I and II families) as well as on a mobile PC processor (Intel Mobile Core 2 Duo T7200). These implementations are evaluated, compared, and discussed in detail. The DSP and the mobile PC implementations, both making heavy use of processor-specific acceleration techniques (intrinsics and resource optimized slicing direct memory access on DSPs or Intel integrated performance primitives Library on mobile PC processors), outperform the FPGA implementations, but at the cost of spending all its resources to these tasks. FPGAs, however, are very well suited to algorithms that benefit from parallel execution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ambrosch, K., Humenberger, M., Kubinger, W., Steininger, A.: Hardware implementation of an SAD based stereo vision algorithm. Proc. Comput. Vis. and Pattern Recognition Work., (2007), doi: 10.1109/CVPR.2007.383417.
Altera Corporation, 101 Innovation Drive, San Jose, CA 95134: Stratix Device Handbook, Vol. 1, Apr 2003.
Altera Corporation, 101 Innovation Drive, San Jose, CA 95134: Stratix II Device Handbook, Vol. 1, Jan 2005.
Azad, P., Gockel, T., Dillmann, R.: Computer Vision, Elektor-Verl. GmbH (2007).
Basler Cooperation, Basler A600f User’s Manual, Document Number DA00056107 (2005).
Bosi, B., Savaria, Y., Bois, G.: Reconfigurable pipelined 2-D convolvers for fast digital signal processing, IEEE Trans. Very Large Scale Integr. Syst., 7(3), pp. 299-308 (1999).
Eckel, C., Bodenstorfer, E., Nachtnebel, H., Roessler, P., Fuertler, J., Mayer, K.: Hoch-schwindigkeits-mera mit intelligenter Datenvorverarbeitung. Proc. of the Austrochip 2006, pp. 103-108 (2006), ISBN 3-200-00770-2.
Fuertler, J., Roessler, P., Brodersen, J., Nachtnebel, H., Mayer, K., Cadek, G., Eckel, C.: Design considerations for scalable high-performance vision systems embedded in industrial print inspection machines, EURASIP Journal on Embed. Syst. (2007) doi:10.1155/2007/71794.
Gonzalez, R.C., Woods, R.E.: Digital Image Processing, Second Ed., Pearson Educa. Int. (2002).
Intel Corporation, 2200 Mission College Blvd, Santa Clara, CA 95054: Intel Integrated Performance Primitives for Intel Architecture, Doc. Number:A70805-014, Version-014, (2004).
Jones, W.D.: Keeping cars from crashing. IEEE Spectr. 38(9), (2001).
Kimmel, R.: Demosaicing: Image reconstruction from color CCD samples. IEEE Trans. on Image Process., pp. 1221-1228 (1999).
Kisačanin, B.: Examples of low-level computer vision on media processors. Proc. IEEE CVPR, ECV Workshop, 2005.
Koc, I.S.: Design considerations for real-time systems with DSP and RISC architectures. Proc. of the EUSIPCO2005 13th Eur. Signal Process. Conf., (2005).
Monaghan, S., Cowen, C.P., Reconfigurable Multi-Bit Processor for DSP Applications in Statistical Physics, Master Thesis, Department of Electric Systems Engineering, University of Essex (1993).
Murphy, R.R.: Rescue robotics for Homeland Security. Commun. of the ACM, pp. 66-68 (2004).
Texas Instruments Incorporated. TMS320C6000 Optimizing Compiler User‘s Guide, Jul 2005, Lit. Number: SPRU187N, http://www.ti.com/litv/pdf/spru187n.
Texas Instruments Incorporated. TMS320C6000 Programmer‘s Guide, Mar 2006, Lit. Number: SPRU198I, http://www.ti.com/litv/pdf/spru198i.
Texas Instruments Incorporated. TMS320C6000 Instruction Set Simulator, Apr 2007, Lit. Number: SPRU600I, http://www.ti.com/litv/pdf/spru600i.
Texas Instruments Incorporated. TMS320C64x+ DSP Image/Video Processing Library (v2.0), Oct 2007, Lit. Number: SPRUF30, http://www.ti.com/litv/pdf/spruf30.
Texas Instruments Incorporated. TMS320C6414T, TMS320C6415T, TMS320C6416T Fixed-Point Digital Signal Processors, Jan 2008, Lit. Number: SPRS226K, http://focus.ti.com/lit/ds/sprs226l/sprs226l_OnlinePDF.pdf.
Tilera Corporation, 2333 Zanker Road, San Jose, California 95131: TILE64 Processor, http://www.tilera.com/products/processors.php. Cited 21 Feb 2008.
Travis, W., Daily, R., Bevly, D.M., Knoedler, K., Behringer, R., Hemetsberger, H., Kogler, J., Kubinger, W., Alefs, B.: SciAutonics-Auburn Engineering’s low-cost, high-speed ATV for the 2005 DARPA Grand Challenge. Journal of Field Robotics 23, pp. 579-597 (2006).
Williams, R.: Using FPGAs for DSP image processing, FPGA and Struct. ASIC Journal (2004), available from http://www.fpgajournal.com/. Cited 5 Feb 2008.
Wirth, M., Fraschini, M., Masek, M., Bruynooghe, M.: Performance evaluation in image processing, EURASIP Journal on Appl. Signal Process. (2006) doi: 10.1155/ASP/2006/45742.
Xilinx Incorporation, 2100 Logic Drive, San Jose, CA 95124-3400: Virtex-5 Family Overview, Datasheet DS100 (v3.0), Feb 2007.
Zinner, C., Kubinger, W.: ROS-DMA: A DMA double buffering method for embedded image processing with resource optimized slicing. Proc. of RTAS 2006, pp. 361-372 (2006).
Zinner, C., Kubinger, W., Isaacs, R.: PfeLib – A performance primitives library for embedded vision, EURASIP Journal on Embed. Syst. (2007) doi:10.1155/2007/49051.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag London Limited
About this chapter
Cite this chapter
Baumgartner, D., Roessler, P., Kubinger, W., Zinner, C., Ambrosch, K. (2009). Benchmarks of Low-Level Vision Algorithms for DSP, FPGA, and Mobile PC Processors. In: Kisačanin, B., Bhattacharyya, S.S., Chai, S. (eds) Embedded Computer Vision. Advances in Computer Vision and Pattern Recognition. Springer, London. https://doi.org/10.1007/978-1-84800-304-0_5
Download citation
DOI: https://doi.org/10.1007/978-1-84800-304-0_5
Publisher Name: Springer, London
Print ISBN: 978-1-84800-303-3
Online ISBN: 978-1-84800-304-0
eBook Packages: Computer ScienceComputer Science (R0)