GPU acceleration of edge detection algorithm based on local variance and integral image: application to air bubbles boundaries extraction
Bettaieb Afef, Filali Nabila, Filali Taoufik, Ben Aissia Habib

 

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

 PDF

Abstract:
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.

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

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

References:

  1. Bian Y, Dong F, Zhang W, Wang H, Tan C, Zhang Z. 3D reconstruction of single rising bubble in water using digital image processing and characteristic matrix, Particuology 2013; 11: 170-183.
  2. Thomanek K, Zielinski1 O, Sahling H, Bohrmann G. Automated gas bubble imaging at sea floor: A new method of in situ gas flux quantification. Ocean Science 2010; 6: 549-562.
  3. Jordt A, Zelenka C, Deimling JS, Koch R, Koser K. The bubble box: Towards an automated visual sensor for 3D analysis and characterization of marine gas release sites. Sensors 2015; 15: 30716-30735.
  4. Bian Y, Dong F, Wang H. Reconstruction of rising bubble with digital image processing method. IEEE International Instrumentation and Measurement Technology Conference 2011.
  5. Paz C, Conde M, Porteiro J, Concheiro M. On the application of image processing methods for bubble recognition to the study of subcooled flow boiling of water in rectangular channels. Sensors 2017; 17(6): 1448.
  6. Zhong S, Zou X, Zhang Z, Tian H. A flexible image analysis method for measuring bubble parameters. Chemical Engineering Science 2016; 141: 143-153.
  7. Al-Lashi RS, Gunn SR, Czerski H. Automated processing of oceanic bubble images for measuring bubble size distributions underneath breaking waves. Journal of Atmospheric and Oceanic Technology 2016; 33(8): 1701-1714.
  8. Yang Z, Zhu Y, Pu Y. Parallel image processing based on CUDA. International Conference on Computer Science and Software Engineering 2008: 198-201.
  9. Fung J, Mann S, Aimone C. OpenVIDIA: Parallel GPU computer vision. Proceedings of the 13th Annual ACM International Conference on Multimedia 2005: 849-852.
  10. Smelyanskiy M, Holmes D, Chhugani J, Larson A, Carmean DM, Hanson D, Dubey P, Augustine K, Kim D, Kyker A, Lee VW, Nguyen AD, Seiler L, Robb R. Mapping high-fidelity volume rendering for medical imaging to CPU, GPU and many-core architectures. IEEE Transactions on Visualization and Computer Graphics 2009; 15(6): 1563-1570.
  11. Cao T, Tang K, Mohamed A, Tan TS. Parallel Banding Algorithm to compute exact distance transform with the GPU. In Book: InI3D’10 Proceedings of the 2010 ACMSIGGRAPH symposium on Inetractive 3D Graphics and Games. New York, NY: ACM; 2010: 83-90.
  12. Barnat J, Bauch P, Brim L, Ceska M. Computing strongly connected components in parallel on CUDA. Technical Report FIMU-RS-2010-10, Brno: Faculty of Informatics, Masaryk University; 2010.
  13. Duvenhage B, Delport JP, Villiers J. Implementation of the Lucas-Kanade image registration algorithm on a GPU for 3D computational platform stabilization. In Book: 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, Liu H, Cao WM, Feng JQ. Multispectral image edge detection via Clifford gradient. Sci China Inf Sci 2012; 55: 260-269.
  15. Zhang X, Liu C. An ideal image edge detection scheme. Multidimens Syst Signal Process 2014; 25(4): 659-681.
  16. Melin P, Gonzalez CI, Castro JR, Mendoza O, Castillo O. Edge-detection method for image processing based on generalized type-2 fuzzy logic. IEEE Trans Fuzzy Syst 2014; 22: 1515-1525.
  17. Díaz-Pernil D, Berciano A, Peña-Cantillana F, Gutiérrez-Naranjo M. A segmenting images with gradient-based edge detection using membrane computing. Pattern Recogn Lett 2013; 34: 846-855.
  18. Guo Y, Şengür A. A novel image edge detection algorithm based on neutrosophic set. Comput Electr Eng 2014; 40: 3-25.
  19. Naidu DL, Rao ChS, Satapathy S. A hybrid approach for image edge detection using neural network and particle Swarm optimization. Proceedings of the 49th Annual Convention of the Computer Society of India (CSI) 2015; 1: 1-9.
  20. Gu J, Pan Y, Wang H. Research on the improvement of image edge detection algorithm based on artificial neural network. Optik 2015; 126: 2974-2978.
  21. Gonzalez CI, Melin P, Castro JR, Mendoza O, Castillo O. Color image edge detection method based on interval type-2 fuzzy systems. In Book: Melin P, Castillo O, Kacprzyk J, eds. Design of intelligent systems based on fuzzy logic, neural networks nature-inspired optimization. Switzerland: Springer International Publishing; 2015: 3-11.
  22. Shui PL, Zhang WC. Noise robust edge detector combining isotropic and anisotropic Gaussian kernels. Pattern Recognition 2012; 45(2): 806-820.
  23. Lopez-Molina C, Vidal-Diez de Ulzurrun G, Bateens JM, Van den Bulcke J, De Bates B. Unsupervised ridge detection using second order anisotropic Gaussian kernels. Signal Processing 2015; 116: 55-67.
  24. Li S, Dasmahapatra S, Maharatna K. Dynamical system approach for edge detection using coupled FitzHugh-Nagumo neurons. IEEE Trans Image Process 2015; 24: 5206-5220.
  25. Dollár P, Zitnick CL. Fast edge detection using structured forests. IEEE Trans Pattern Anal Mach Intell 2015; 37: 1558-1570.
  26. Lopez-Molina C, Galar M, Bustince H, De Bates B. On the impact of anisotropic diffusion on edge detection. Pattern Recognition 2014; 47: 270-281.
  27. Miguel A, Poo D, Odone F, De Vito E. Edge and corner with shearlets. IEEE Trans Image Proces 2015; 24: 3768-3781.
  28. Lopez-Molina C, De Bates B, Bustince H, Sanz J, Barrenechea E. Multi-scale edge detection based on Gaussian smoothing and edge tracking. Knowledge-Based Systems 2013; 44: 101-111.
  29. Zhenxing W, Xi L, Yong D. Image edge detection based on local dimension: a complex networks approach. Physica A 2015; 440: 9-18.
  30. Azeroual A, Afdel K. Fast image edge detection based on faber schauder wavelet and otsu threshold. Heliyon 2017; 3(12): e00485.
  31. Medina-Carnicer R, Carmona-Poyato A, Munoz-alinas R, Madrid-Cuevas FJ. Determining hysteresis thresholds for edge detection by combining the advantages and disadvantages of thresholding methods. IEEE Transactions on Image Processing 2010; 19(1): 165-173.
  32. Laligant O, Truchetet F. A nonlinear derivative scheme applied to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 2010; 32(2): P. 242-257.
  33. Sri Krishna A, Eswara RB, Pompapathi M. Nonlinear noise suppression edge detection scheme for noisy images. International Conference on Recent Advances and Innovations in Engineering (ICRAIE) 2014: 1-6.
  34. Pawar KB, Nalbalwar SL. Distributed canny edge detection algorithm using morphological filter. IEEE International Conference on Recent Trends In Electronics, Information & Communication Technology (RTEICT) 2016: 1523-1527.
  35. Golpayegani N, Ashoori A. A novel algorithm for edge enhancement based on Hilbert Matrix. 2nd International Conference on Computer Engineering and Technology 2010: V1-579-V1-581.
  36. Sghaier MO, Coulibaly I, Lepage R. A novel approach toward rapid road mapping based on beamlet transform. IEEE Geoscience and Remote Sensing Symposium 2014; 2351-2354.
  37. Biswas R, Sil J. An improved canny edge detection algorithm based on type-2 fuzzy sets. 2nd International Conference on Computer, Communication, Control and Information Technology (C3IT-2012) 2012; 4: 820-824.
  38. Dollar P, Zitnick CL. Fast edge detection using structured forests. IEEE Transactions on Pattern Analysis and Machine Intelligence 2015; 37(8): 1558-1570.
  39. Fu W, Johnston M, Zhang M. Low-level feature extraction for edge detection using genetic programming. IEEE Transactions on Cybernetics 2014; 44(8): 1459-1472.
  40. Gong HX, Hao L. Roberts edge detection algorithm based on GPU. Journal of Chemical and Pharmaceutical Research 2014; 6: 1308-1314.
  41. Barbaro M. Accelerating the Canny edge detection algorithm with CUDA/GPU. International Congress COMPUMAT 2015.
© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846)332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20