(43-3) 13 * << * >> * Русский * English * Содержание * Все выпуски

GPU acceleration of edge detection algorithm based on local variance and integral image: application to air bubbles boundaries extraction

Afef Bettaieb, Nabila Filali, Taoufik Filali, Habib Ben Aissia

Laboratory of Metrology and Energetic Systems, National School of Engineers of Monastir, University of Monastir

 PDF, 713 kB

DOI: 10.18287/2412-6179-2019-43-3-446-454

Страницы: 446-454.

Аннотация:
Accurate detection of air bubbles boundaries is of crucial importance in determining the performance and in the study of various gas/liquid two-phase flow systems. The main goal of this work is edge extraction of air bubbles rising in two-phase flow in real-time. To accomplish this, a fast algorithm based on local variance is improved and accelerated on the GPU to detect bubble contour. The proposed method is robust against changes of intensity contrast of edges and capable of giving high detection responses on low contrast edges. This algorithm is performed in two steps: in the first step, the local variance of each pixel is computed based on integral image, and then the resulting contours are thinned to generate the final edge map. We have implemented our algorithm on an NVIDIA GTX 780 GPU. The parallel implementation of our algorithm gives a speedup factor equal to 17x for high resolution images (1024×1024 pixels) compared to the serial implementation. Also, quantitative and qualitative assessments of our algorithm versus the most common edge detection algorithms from the literature were performed. A remarkable performance in terms of results accuracy and computation time is achieved with our algorithm.

Ключевые слова:
GPU, CUDA, real-time, digital image processing, edge detection, air bubbles

Цитирование:
Bettaieb, A.
GPU acceleration of edge detection algorithm based on local variance and integral image: application to air bubbles boundaries extraction / A. Bettaieb, N. Filali, T. Filali, H. Ben Aissia // Computer Optics. – 2019. – Vol. 43(3). – P. 446-454. – DOI: 10.18287/2412-6179-2019-43-3-446-454.

Литература:

  1. Bian, Y. 3D reconstruction of single rising bubble in water using digital image processing and characteristic matrix / Y. Bian, F. Dong, W. Zhang, H. Wang, C. Tan, Z. Zhang // Particuologyю – 2013. – Vol. 11. – P. 170-183.
  2. Thomanek, K. Automated gas bubble imaging at sea floor: A new method of in situ gas flux quantification / K. Thomanek, O. Zielinski1, H. Sahling, G. Bohrmann // Ocean Science. – 2010. – Vol. 6. – P. 549-562.
  3. Jordt, A. The bubble box: Towards an automated visual sensor for 3D analysis and characterization of marine gas release sites / A. Jordt, C. Zelenka, J.S. Deimling, R. Koch, K. Koser // Sensors. – 2015. – Vol. 15. – P. 30716-30735.
  4. Bian, Y. Reconstruction of rising bubble with digital image processing method / Y. Bian, F. Dong, H. Wang // IEEE International Instrumentation and Measurement Technology Conference. – 2011.
  5. Paz, C. On the application of image processing methods for bubble recognition to the study of subcooled flow boiling of water in rectangular channels / C. Paz, M. Conde, J. Porteiro, M. Concheiro // Sensors. – 2017. – Vol. 17, Issue 6. – 1448.
  6. ZhongS. A flexible image analysis method for measuring bubble parameters / S. Zhong, X. Zou, Z. Zhang, H. Tian // Chemical Engineering Science. – 2016. – Vol. 141. – P. 143-153.
  7. Al-Lashi, R.S. Automated processing of oceanic bubble images for measuring bubble size distributions underneath breaking waves / R.S. Al-Lashi, S.R. Gunn, H. Czerski // Journal of Atmospheric and Oceanic Technology. – 2016. – Vol. 33, Issue 8. – P. 1701-1714.
  8. Yang, Z. Parallel image processing based on CUDA / Z. Yang, Y. Zhu, Y. Pu // International Conference on Computer Science and Software Engineering. – 2008. – P. 198-201.
  9. Fung, J. OpenVIDIA: Parallel GPU computer vision / J. Fung, S. Mann, C. Aimone // Proceedings of the 13th Annual ACM International Conference on Multimedia. – 2005. – P. 849-852.
  10. Smelyanskiy, M. Mapping high-fidelity volume rendering for medical imaging to CPU, GPU and many-core architectures / M. Smelyanskiy, D. Holmes, J. Chhugani, A. Larson, D.M. Carmean, D. Hanson, P. Dubey, K. Augustine, D. Kim, A. Kyker, V.W. Lee, A.D. Nguyen, L. Seiler, R. Robb // IEEE Transactions on Visualization and Computer Graphics. – 2009. – Vol. 15, Issue 6. – P. 1563-1570.
  11. Cao, T. Parallel Banding Algorithm to compute exact distance transform with the GPU / T. Cao, K. Tang, A. Mohamed, T.S. Tan. – In:InI3D’10 Proceedings of the 2010 ACMSIGGRAPH symposium on Inetractive 3D Graphics and Games. – New York, NY: ACM, 2010. – P. 83-90.
  12. Barnat, J. Computing strongly connected components in parallel on CUDA / J. Barnat, P. Bauch, L. Brim, M. Ceska // Technical Report FIMU-RS-2010-10, Brno: Faculty of Informatics, Masaryk University, 2010.
  13. Duvenhage, B. Implementation of the Lucas-Kanade image registration algorithm on a GPU for 3D computational platform stabilization / B. Duvenhage, J.P. Delport, J. Villiers // In: AFRIGRAPH ’10 Proceedings of the 7th International Conference on Computer Graphics, Virtual Reality, Visualisation and Interaction in Africa. – New York, NY: ACM, 2010. – P. 83-90.
  14. Xu, C. Multispectral image edge detection via Clifford gradient / C. Xu, H. Liu, W.M. Cao, J.Q. Feng // Science China Information Sciences. – 2012. – Vol. 55. – P. 260-269.
  15. Zhang, X. An ideal image edge detection scheme / X. Zhang, C. Liu // Multidimensional Systems and Signal Processing. – 2014. – Vol. 25, Issue 4. – P. 659-681.
  16. Melin, P. Edge-detection method for image processing based on generalized type-2 fuzzy logic / P. Melin, C.I. Gonzalez, J.R. Castro, O. Mendoza, O. Castillo // IEEE Transactions on Fuzzy Systems. – 2014. – Vol. 22. – P. 1515-1525.
  17. Díaz-Pernil, D. A segmenting images with gradient-based edge detection using membrane computing / D. Díaz-Pernil, A. Berciano, F. Peña-Cantillana, M. Gutiérrez-Naranjo // Pattern Recognition Letters. – 2013. – Vol. 34. – P. 846-855.
  18. Guo, Y. A novel image edge detection algorithm based on neutrosophic set / Y. Guo, A. Şengür // Computers & Electrical Engineering. – 2014. – Vol. 40. – P. 3-25.
  19. Naidu, D.L. A hybrid approach for image edge detection using neural network and particle Swarm optimization / D.L. Naidu, Ch.S. Rao, S. Satapathy // Proceedings of the 49th Annual Convention of the Computer Society of India (CSI). – 2015. – Vol. 1. – P. 1-9.
  20. Gu, J. Research on the improvement of image edge detection algorithm based on artificial neural network / J. Gu, Y. Pan, H. Wang // Optik. – 2015. – Vol. 126. – P. 2974-2978.
  21. Gonzalez, C.I. Color image edge detection method based on interval type-2 fuzzy systems / C.I. Gonzalez, P. Melin, J.R. Castro, O. Mendoza, O. Castillo. – In: Design of intelligent systems based on fuzzy logic, neural networks nature-inspired optimization / ed. by P. Melin, O. Castillo, J. Kacprzyk. – Switzerland: Springer International Publishing, 2015. – P. 3-11.
  22. Shui, P.L. Noise robust edge detector combining isotropic and anisotropic Gaussian kernels / P.L. Shui, W.C. Zhang // Pattern Recognition. – 2012. – Vol. 45, Issue 2. – P. 806-820.
  23. Lopez-Molina, C. Unsupervised ridge detection using second order anisotropic Gaussian kernels / C. Lopez-Molina, G. Vidal-Diez de Ulzurrun, J.M. Bateens, J. Van den Bulcke, B De Bates // Signal Processing. – 2015. – Vol. 116. – P. 55-67.
  24. Li, S. Dynamical system approach for edge detection using coupled FitzHugh-Nagumo neurons / S. Li, S. Dasmahapatra, K. Maharatna // IEEE Transactions on Image Processing. – 2015. – Vol. 24. – P. 5206-5220.
  25. Dollár, P. Fast edge detection using structured forests / P. Dollár, CL. Zitnick // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2015. – Vol. 37. – P. 1558-1570
  26. Lopez-Molina, C. On the impact of anisotropic diffusion on edge detection / C. Lopez-Molina, M. Galar, H. Bustince, B. De Bates // Pattern Recognition. – 2014. – Vol. 47. – P. 270-281.
  27. Miguel, A. Edge and corner with shearlets / A. Miguel, D. Poo, F. Odone, E. De Vito // IEEE Transactions on Image Processing. – 2015. – Vol. 24. – P. 3768-3781.
  28. Lopez-Molina, C. Multi-scale edge detection based on Gaussian smoothing and edge tracking / C. Lopez-Molina, B. De Bates, H. Bustince, J. Sanz, E. Barrenechea // Knowledge-Based Systems. – 2013. – Vol. 44. – P. 101-111.
  29. Zhenxing, W. Image edge detection based on local dimension: a complex networks approach / W. Zhenxing, L. Xi, D. Yong // Physica A: Statistical Mechanics and its Applications. – 2015. – Vol. 440. – P. 9-18.
  30. Azeroual, A. Fast image edge detection based on faber schauder wavelet and otsu threshold / A. Azeroual, K. Afdel // Heliyon. – 2017. – Vol. 3, Issue 12. – e00485.
  31. Medina-Carnicer, R. Determining hysteresis thresholds for edge detection by combining the advantages and disadvantages of thresholding methods / R. Medina-Carnicer, A. Carmona-Poyato, R. Munoz-Salinas, F.J. Madrid-Cuevas // IEEE Transactions on Image Processing. – 2010. – Vol. 19, Issue 1. – P. 165-173.
  32. Laligant, O. A nonlinear derivative scheme applied to edge detection / O. Laligant, F. Truchetet // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2010. – Vol. 32, Issue 2. – P. 242-257.
  33. Sri Krishna, A. Nonlinear noise suppression edge detection scheme for noisy images / A. Sri Krishna, R.B. Eswara, M. Pompapathi // International Conference on Recent Advances and Innovations in Engineering (ICRAIE). – 2014. – P. 1-6.
  34. Pawar, K.B. Distributed canny edge detection algorithm using morphological filter / K.B. Pawar, S.L. Nalbalwar // IEEE International Conference on Recent Trends In Electronics, Information & Communication Technology (RTEICT). – 2016. – P. 1523-1527.
  35. Golpayegani, N. A novel algorithm for edge enhancement based on Hilbert Matrix / N. Golpayegani, A. Ashoori // 2nd International Conference on Computer Engineering and Technology. – 2010. – P. V1-579-V1-581.
  36. Sghaier, M.O. A novel approach toward rapid road mapping based on beamlet transform / M.O. Sghaier, I. Coulibaly, R. Lepage // IEEE Geoscience and Remote Sensing Symposium. – 2014. – P. 2351-2354.
  37. Biswas, R. An improved canny edge detection algorithm based on type-2 fuzzy sets / R. Biswas, J. Sil // 2nd International Conference on Computer, Communication, Control and Information Technology (C3IT-2012). – 2012. – Vol. 4. – P. 820-824.
  38. Dollar, P. Fast edge detection using structured forests / P. Dollar, C.L. Zitnick // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2015. – Vol. 37, Issue 8. – P. 1558-1570.
  39. Fu, W. Low-level feature extraction for edge detection using genetic programming / W. Fu, M. Johnston, M. Zhang // IEEE Transactions on Cybernetics. – 2014. – Vol. 44, Issue 8. – P. 1459-1472.
  40. Gong, H.X. Roberts edge detection algorithm based on GPU / H.X. Gong, L. Hao // Journal of Chemical and Pharmaceutical Research. – 2014. – Vol. 6. – P. 1308-1314.
  41. Barbaro, M. Accelerating the Canny edge detection algorithm with CUDA/GPU / M. Barbaro // International Congress COMPUMAT 2015. – 2015..

© 2009, IPSI RAS
Россия, 443001, Самара, ул. Молодогвардейская, 151; электронная почта: journal@computeroptics.ru ; тел: +7 (846) 242-41-24 (ответственный секретарь), +7 (846) 332-56-22 (технический редактор), факс: +7 (846) 332-56-20