GrayScaleAccel: Acelerador de Escala de Cinza em FPGA
Resumo
Neste artigo é apresentado o GrayScaleAccel, uma solução HardwareSoftware que acelera um algoritmo de escala de cinza em até 183 vezes comparado a versão puramente em software. Este acelerador utiliza a placa Ultra96 e o framework PYNQ que favorecem esta solução devido a plataforma ter processador e FPGA fortemente integrados e ser compatível com framework de alta produtividade em Python. Os resultados de síntese ainda sugerem que há muitos recursos no FPGA para serem utilizados para exploração de paralelismo desta aplicação ou outras ainda mais ambiciosas.Referências
Andersson, S. ([S.d.]). Zynq design from scratch. Part 41. http://svenand.blogdrives.com/archive/202.html#.XQQwgojMOUl.
Bukhari, S. S., Breuel, T. M. and Shafait, F. (2009). Textline information extraction from grayscale camera-captured document images. In 2009 16th IEEE International Conference on Image Processing (ICIP).
Ding, W., Kang, B., Zhou, Q., Lin, M. and Zhang, S. (2019). Grayscale-thermal Tracking via Canonical Correlation Analysis Based Inverse Sparse Representation. In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Elsaadouny, M., Barowski, J. and Rolfes, I. (2020). FPGA Based Accelerator for Buried Objects Identification. In 2020 43rd International Conference on Telecommunications and Signal Processing (TSP).
Kanan, C. and Cottrell, G. W. (2012). Color-to-Grayscale: Does the Method Matter in Image Recognition? PLOS ONE, v. 7, n. 1, p. e29740.
Kang, B., Liang, D., Ding, W., Zhou, H. and Zhu, W.-P. (2020). Grayscale-Thermal Tracking via Inverse Sparse Representation-Based Collaborative Encoding. IEEE Transactions on Image Processing, v. 29, p. 3401–3415.
Papamarkou, I. and Papamarkos, N. (2013). Conversion of color documents to grayscale. In 21st Mediterranean Conference on Control and Automation.
Rybalkin, V., Pappalardo, A., Ghaffar, M. M., et al. (2018). FINN-L: Library Extensions and Design Trade-off Analysis for Variable Precision LSTM Networks on FPGAs. arXiv:1807.04093.
Shaher, I. M., Mahmoud, M., Ibrahim, H., Ali, M. and Mostafa, H. (2020). Implementation of a Hardware Accelerator for a Real-time Encryption System. In 2020 IEEE 63rd International Midwest Symposium on Circuits and Systems (MWSCAS).
Stornaiuolo, L., Santambrogio, M. and Sciuto, D. (2018). On How to Efficiently Implement Deep Learning Algorithms on PYNQ Platform. In 2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI).
Stornaiuolo, L., Perini, M., Santambrogio, M. D. and Sciuto, D. (2019). FPGA-Based Embedded System Implementation of Audio Signal Alignment. In 2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW).
Vohra, M. and Fasciani, S. (2019). PYNQ- Torch: a framework to develop PyTorch accelerators on the PYNQ platform. In 2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).
Yan, J.-J., Kuo, H.-H., Lin, Y.-F. and Liao, T.-L. (2016). Real-Time Driver Drowsiness Detection System Based on PERCLOS and Grayscale Image Processing. In 2016 International Symposium on Computer, Consumer and Control (IS3C).
Bukhari, S. S., Breuel, T. M. and Shafait, F. (2009). Textline information extraction from grayscale camera-captured document images. In 2009 16th IEEE International Conference on Image Processing (ICIP).
Ding, W., Kang, B., Zhou, Q., Lin, M. and Zhang, S. (2019). Grayscale-thermal Tracking via Canonical Correlation Analysis Based Inverse Sparse Representation. In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Elsaadouny, M., Barowski, J. and Rolfes, I. (2020). FPGA Based Accelerator for Buried Objects Identification. In 2020 43rd International Conference on Telecommunications and Signal Processing (TSP).
Kanan, C. and Cottrell, G. W. (2012). Color-to-Grayscale: Does the Method Matter in Image Recognition? PLOS ONE, v. 7, n. 1, p. e29740.
Kang, B., Liang, D., Ding, W., Zhou, H. and Zhu, W.-P. (2020). Grayscale-Thermal Tracking via Inverse Sparse Representation-Based Collaborative Encoding. IEEE Transactions on Image Processing, v. 29, p. 3401–3415.
Papamarkou, I. and Papamarkos, N. (2013). Conversion of color documents to grayscale. In 21st Mediterranean Conference on Control and Automation.
Rybalkin, V., Pappalardo, A., Ghaffar, M. M., et al. (2018). FINN-L: Library Extensions and Design Trade-off Analysis for Variable Precision LSTM Networks on FPGAs. arXiv:1807.04093.
Shaher, I. M., Mahmoud, M., Ibrahim, H., Ali, M. and Mostafa, H. (2020). Implementation of a Hardware Accelerator for a Real-time Encryption System. In 2020 IEEE 63rd International Midwest Symposium on Circuits and Systems (MWSCAS).
Stornaiuolo, L., Santambrogio, M. and Sciuto, D. (2018). On How to Efficiently Implement Deep Learning Algorithms on PYNQ Platform. In 2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI).
Stornaiuolo, L., Perini, M., Santambrogio, M. D. and Sciuto, D. (2019). FPGA-Based Embedded System Implementation of Audio Signal Alignment. In 2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW).
Vohra, M. and Fasciani, S. (2019). PYNQ- Torch: a framework to develop PyTorch accelerators on the PYNQ platform. In 2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).
Yan, J.-J., Kuo, H.-H., Lin, Y.-F. and Liao, T.-L. (2016). Real-Time Driver Drowsiness Detection System Based on PERCLOS and Grayscale Image Processing. In 2016 International Symposium on Computer, Consumer and Control (IS3C).
Publicado
21/10/2020
Como Citar
S. E SILVA, Thomas; FERNANDES, Arlindo; FERNANDES, Sílvio.
GrayScaleAccel: Acelerador de Escala de Cinza em FPGA. In: WORKSHOP DE INICIAÇÃO CIENTÍFICA - SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 21. , 2020, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 14-21.
DOI: https://doi.org/10.5753/wscad_estendido.2020.14084.
