Level set method based segmentation provides an efficient tool for topological and geometrical shape handling, but it is slow due to high computational burden. In this work, we provide a framework for streaming computations on large volumetric images on the GPU. Our streaming computational model allows processing large amounts of data with small memory footprint. We show volumetric segmentation using a higher order, multi-phase level set method with speedups of the order of 5~10 times.
O. Sharma, Q. Zhang, F. Anton, and C. Bajaj, “Fast streaming 3D level set segmentation on the GPU for smooth multi-phase segmentation,” in Transactions on computational science XIII, Springer Berlin Heidelberg, 2011, pp. 72-91.
O. Sharma, Q. Zhang, F. Anton, and C. Bajaj, “Multi-domain, higher order level set scheme for 3D image segmentation on the GPU,” in Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, 2010, pp. 2211-2216.
O. Sharma and F. Anton, “CUDA based level set method for 3D reconstruction of fishes from large acoustic data,” in International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG), 2009, pp. 153-160.