Fig 2 - uploaded by Francis Quek
Content may be subject to copyright.
Overview of the robust facet image modeling algorithm. 

Overview of the robust facet image modeling algorithm. 

Source publication
Article
Full-text available
Modern graphics processing units (GPUs) are commodity data-parallel coprocessors capable of high performance computation and data throughput. It is well known that the GPUs are ideal implementation platforms for image processing applications. However, the level of efforts and expertise to optimize the application performance is still substantial. T...

Context in source publication

Context 1
... the QR factorization is done with Householder transformations, a series of orthogonal transformations applied to the input matrix A to bring it into upper triangular form. The product of these orthogonal transformations is the matrix Q t giving Q t A = R. Figure 2 outlines the algorithm for IRLS-based Robust FIM. Given an n × m window, several different order robust surface fits for a pixel are computed up to a preselected maximum order. ...

Similar publications

Conference Paper
Full-text available
The connection between Internet of Things (IoT) and High Performance Computing (HPC) is investigated in this keynote presentation. New paradigms and devices for HPC are presented. Several examples related to smart building management, smart logistics and smart manufacturing leading to difficult combinatorial optimization problems are detailed.
Conference Paper
Full-text available
The incorporation of GPUs as co-processors has brought forth significant performance improvements for High-Performance Computing (HPC). Efficient utilization of the GPU resources is thus an important consideration for computer scientists. In order to obtain the required performance while limiting the energy consumption, researchers and vendors alik...
Article
Full-text available
We present a multipole-based N-body solver for 3D multiresolution, block-structured grids. The solver is designed for a single heterogeneous CPU/GPU compute node, and evaluates the multipole expansions on the CPU while offloading the compute-heavy particle-particle interactions to the GPU. The regular structure of the destination points is exploite...
Preprint
Full-text available
During the past decades, evolutionary computation (EC) has demonstrated promising potential in solving various complex optimization problems of relatively small scales. Nowadays, however, ongoing developments in modern science and engineering are bringing increasingly grave challenges to the conventional EC paradigm in terms of scalability. As prob...
Conference Paper
Full-text available
The risk of space debris is now perceived as primordial by governments and international space agencies. Since the last decade, international space agencies have developed tools simulate the re-entry of satellites and orbital stations in order to assess casualty risk on the ground. Nevertheless, all current tools provide deterministic solutions, th...

Citations

... An analogy may help to explain the significance of this 'purpose-oriented' approach to embodied interaction. For our analogy, consider the GPGPU approach to computing [7,8] where high-speed architectures designed for graphics are appropriated for general purpose computing. There is no single model behind the way memory, processor pipelines, and buses are designed for particular GPUs. ...
Chapter
Full-text available
We shall explore interaction on a touch surface in two domains. In the first, we shall look at a system that enables Individuals with Blindness or Severe Visual Impairment (IBSVI) to read at their own pace. We show how reading and information access are inherently embodied activities, and how touch interaction can support reading for IBSVI. In the second project, we will investigate one of the challenges of spatial knowledge acquisition while moving through large virtual spaces. The widespread availability of consumer HDTVs with 3D capability have brought them within reach of use in classroom and other learning environments. We demonstrate how transferring walking action to the hand and fingers can enable virtual navigation with benefits in the form of route knowledge, survey knowledge, and perceptual gains over traditional virtual navigation techniques. The technique is lightweight and suitable for widespread use for learning.