Roberts edge detection algorithm based on GPU

With the development of the semiconductor technolog y, the GPU’s floating point computing capacity impr oves rapidly. How to apply the GPU technology to the non-graphic computing field becomes a highlight in the research of high performance computing. The Roberts edge detection ais a typical image processing algorithms. A fast Roberts edge detection algorithm is presented based on GPU, Texture memory technology and asynchronous data transmission are adopted to optimize the applicatio n of the algorithm. The experiment expressed that w e could get a over ten times speed effect by this method than tra ditional Roberts edge detection algorithm.

[1]  Jingjing Yang,et al.  Improvement and parallel implementation of canny edge detection algorithm based on GPU , 2011, 2011 9th IEEE International Conference on ASIC.

[2]  Lin Yi-song.  Design and Implementation of Jacobi and Laplace Algorithms on GPU Platform , 2009 .

[3]  O. R. Vincent,et al.  A Descriptive Algorithm for Sobel Image Edge Detection , 2009 .

[4]  Joseph Ross Mitchell,et al.  A work-efficient GPU algorithm for level set segmentation , 2010, HPG '10.

[5]  David Malah,et al.  A study of edge detection algorithms , 1982, Comput. Graph. Image Process..

[6]  Jie Cheng,et al.  CUDA by Example: An Introduction to General-Purpose GPU Programming , 2010, Scalable Comput. Pract. Exp..

[7]  Nan Zhang,et al.  Image parallel processing based on GPU , 2010, 2010 2nd International Conference on Advanced Computer Control.

[8]  Martin Margala,et al.  Sobel edge detection processor for a real-time volume rendering system , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).

[9]  Arie E. Kaufman,et al.  GPU Cluster for High Performance Computing , 2004, Proceedings of the ACM/IEEE SC2004 Conference.

[10]  Robert M. Farber,et al.  CUDA Application Design and Development , 2011 .