Parallel Banding Algorithm to compute exact distance transform with the GPU
Thanh-Tung Cao,Ke Tang,Anis Mohamed,Tiow-Seng Tan +3 more
- pp 83-90
Reads0
Chats0
TLDR
In this article, a parallel banding algorithm (PBA) was proposed to compute the exact Euclidean distance transform (EDT) for binary images in 2D and higher dimensions.Abstract:
We propose a Parallel Banding Algorithm (PBA) on the GPU to compute the exact Euclidean Distance Transform (EDT) for a binary image in 2D and higher dimensions. Partitioning the image into small bands to process and then merging them concurrently, PBA computes the exact EDT with optimal linear total work, high level of parallelism and a good memory access pattern. This work is the first attempt to exploit the enormous power of the GPU in computing the exact EDT, while prior works are only on approximation. Compared to these other algorithms in our experiments, our exact algorithm is still a few times faster in 2D and 3D for most input sizes. We illustrate the use of our algorithm in applications such as computing the Euclidean skeleton using the integer medial axis transform, performing morphological operations of 3D volumetric data, and constructing 2D weighted centroidal Voronoi diagrams.read more
Figures
Figure 1: The original grayscale image (left) to produce the stipple drawing (right) by using weighted centroidal Voronoi diagram. 
Figure 8: Speedup of PBA using optimal m1, m2 and m3, on different number of processors. 
Figure 10: Percentage of running time of the different phases of PBA in 3D with optimized and unoptimized parameters. 
Figure 7: (a) 2D running time, and (b) normalized frame rates of different algorithms. 
Figure 9: (a) 3D running time, and (b) normalized frame rates of different algorithms. 
Figure 11: Illustration of the weighted CVD computation.
Citations
More filters
Journal ArticleDOI
Medical Image Processing on the GPU : Past, Present and Future
TL;DR: This review presents the past and present work on GPU accelerated medical image processing, and is meant to serve as an overview and introduction to existing GPU implementations.
Proceedings ArticleDOI
Voxblox: Incremental 3D Euclidean Signed Distance Fields for on-board MAV planning
TL;DR: This work proposes a method to incrementally build ESDFs from Truncated Signed Distance Fields (TSDFs), a common implicit surface representation used in computer graphics and vision, and shows that it can build TSDFs faster than Octomaps, and that it is more accurate than occupancy maps.
Proceedings ArticleDOI
Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planning
TL;DR: Voxblox as mentioned in this paper uses Euclidean Signed Distance Fields (ESDFs) to generate a surface representation of the environment for a micro-drone in unstructured, unexplored environments.
Journal ArticleDOI
3D skeletons: a state-of-the-art report
TL;DR: A taxonomy of 3D skeletons is proposed which allows us to further analyze and compare them with respect to their properties, and describes several applications of3D skeletons, which illustrate their added value for different shape analysis and processing tasks.
Journal ArticleDOI
Skeleton-Based Edge Bundling for Graph Visualization
TL;DR: A novel approach that combines edge clustering, distance fields, and 2D skeletonization to construct progressively bundled layouts for general graphs by iteratively attracting edges towards the centerlines of level sets of their distance fields.
References
More filters
Least Squares Quantization in PCM
TL;DR: The corresponding result for any finite number of quanta is derived; that is, necessary conditions are found that the quanta and associated quantization intervals of an optimum finite quantization scheme must satisfy.
Journal ArticleDOI
Euclidean distance mapping
TL;DR: It is shown that skeletons can be produced by simple procedures and since these are based on Euclidean distances it is assumed that they are superior to skeletons based on d4−, d8−, and even octagonal metrics.
Journal ArticleDOI
A linear time algorithm for computing exact Euclidean distance transforms of binary images in arbitrary dimensions
TL;DR: The algorithm, which is based on dimensionality reduction and partial Voronoi diagram construction, can be used for computing the DT for a wide class of distance functions, including the L/sub p/ and chamfer metrics.
Parallel Prefix Sum (Scan) with CUDA
TL;DR: The water needs of this region have changed in recent years from being primarily for agricultural purposes to domestic and industrial uses now, and the needs of these industries have changed as well.
Proceedings ArticleDOI
Scan primitives for GPU computing
TL;DR: Using the scan primitives, this work shows novel GPU implementations of quicksort and sparse matrix-vector multiply, and analyzes the performance of the scanPrimitives, several sort algorithms that use the scan Primitives, and a graphical shallow-water fluid simulation using the scan framework for a tridiagonal matrix solver.