FPS performance profiling for multiple computational architectures using the DCP dehazing algorithm
Article Sidebar
Main Article Content
Abstract
In this document we present a benchmark to evaluate the performance of different platforms in the execution of a dehazing algorithm based on the Dark Channel Prior (DCP) [1]. The parameter used for the evaluation was the number of frames per second (FPS) that the device was able to process. This tool allows to determine which architectures can execute the algorithm in real time.
The testing environment was executing in four platforms, a Google Pixel 3a, a Raspberry Pi 3B+, a GPU by NVIDIA, and an Intel x86 processor. The following software development kits (SDK’s) where used for each of the platforms: Android NDK, Yocto Poky, CUDA, and the GCC toolchain.
The tool allowed us to collect, for each platform, the FPS for different image sizes, these results allow the selection of an ideal architecture depending on a specific application (e.g., low power, HPC).
The testing environment was executing in four platforms, a Google Pixel 3a, a Raspberry Pi 3B+, a GPU by NVIDIA, and an Intel x86 processor. The following software development kits (SDK’s) where used for each of the platforms: Android NDK, Yocto Poky, CUDA, and the GCC toolchain.
The tool allowed us to collect, for each platform, the FPS for different image sizes, these results allow the selection of an ideal architecture depending on a specific application (e.g., low power, HPC).
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Los autores conservan los derechos de autor y ceden a la revista el derecho de la primera publicación y pueda editarlo, reproducirlo, distribuirlo, exhibirlo y comunicarlo en el país y en el extranjero mediante medios impresos y electrónicos. Asimismo, asumen el compromiso sobre cualquier litigio o reclamación relacionada con derechos de propiedad intelectual, exonerando de responsabilidad a la Editorial Tecnológica de Costa Rica. Además, se establece que los autores pueden realizar otros acuerdos contractuales independientes y adicionales para la distribución no exclusiva de la versión del artículo publicado en esta revista (p. ej., incluirlo en un repositorio institucional o publicarlo en un libro) siempre que indiquen claramente que el trabajo se publicó por primera vez en esta revista.
References
K. He, J. Suny X. Tang, “Single image haze removal using dark channel prior,” in 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 1956–1963. DOI: 10.1109/CVPR.2009.5206515.
I. Gultepe, R. Tardif, S. C. Michaelides, J. Cermak, A. Bott, J. Bendix, M. D. M¨uller, M. Pagowski, B. Hansen, B. Ellrod, W. Jacobs, G. Tothy S. G. Cober, “Fog research: A review of past achievements and future perspectives,” in Pure and Applied Geophysics, vol. 164, 2007, pp. 1121–1159. DOI: https://doi.org/10.1007/s00024-007-0211-x.
How do weather events impact roads? [En línea]. Disponible: https://ops.fhwa.dot.gov/weather/q1 roadimpact.htm.
K. He, J. Sun y X. Tang, “Single image haze removal using dark channel prior,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 12, pp. 2341–2353, 2011. DOI: 10.1109/TPAMI.2010.168.
L. A. Chavarria-Zamora, S. Arriola-Valverdey R. Rimolo-Donadio, “Evaluation of fog reduction algorithms for photogrammetric applications in agriculture,” in 2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI), 2018, pp. 1–9. DOI: 10.1109/IWOBI.2018.8464186.
G. Harish Babu and N. Venkatram, “A survey on analysis and implementation of state-of-the-art haze removal techniques,” Journal of Visual Communication and Image Representation, vol. 72, p. 102 912, 2020, ISSN: 1047-3203. DOI: https://doi.org/10.1016/j.jvcir.2020.102912. [En línea]. Disponible: http://www.sciencedirect.com/science/article/pii/S1047320320301504.
T. Koga, A. Yasuda, S. Furukaway N. Suetake, “A simplified and fast dehazing processing suitable for embedded systems,” in 2018 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), 2018, pp. 492–497. DOI: 10.1109/ISPACS.2018.8923385.
Y. Iwamoto, N. Hashimotoy Y. Chen, “Fast dark channel prior based haze removal from a single image,” in 2018 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), 2018, pp. 458–461. DOI:10.1109/FSKD.2018.8686854.
J. Perez, P. J. Sanz, M. Brysony S. B. Williams, “A benchmarking study on single image dehazing techniques for underwater autonomous vehicles,” in OCEANS 2017 - Aberdeen, 2017, pp. 1–9.
P. Soma and R. K. Jatoth, “Implementation of a novel, fast and efficient image de hazing algorithm on embedded hardware platforms,” Circuits, Systems, and Signal Processing, Aug. 2020. DOI: 10.1007 / s00034-020-01517-4. [En línea]. Disponible: http://dx.doi.org/10.1007/s00034-020-01517-4.