Neutron computed tomography has become a routine method at many neutron sources due to the availability of digital detection systems, powerful computers and advanced software. The commercial packages Octopus by Inside...
详细信息
Neutron computed tomography has become a routine method at many neutron sources due to the availability of digital detection systems, powerful computers and advanced software. The commercial packages Octopus by Inside Matters and VGStudio by Volume Graphics have been established as a quasi-standard for high-end computed tomography. However, these packages require a stiff investment and are available to the users only on-site at the imaging facility to do their data processing. There is a demand from users to have imageprocessing software at home to do further data processing;in addition, neutron computed tomography is now being introduced even at smaller and older reactors. Operators need to show a first working tomography setup before they can obtain a budget to build an advanced tomography system. Several packages are available on the web for free;however, these have been developed for x-rays or synchrotron radiation and are not immediately useable for neutron computed tomography. Three reconstruction packages and three 3D-viewers have been identified and used even for Gigabyte datasets. This paper is not a scientific publication in the classic sense, but is intended as a review to provide searchable help to make the described packages usable for the tomography community. It presents the necessary additional preprocessing in imageJ, some workarounds for bugs in the software, and undocumented or badly documented parameters that need to be adapted for neutron computed tomography. The result is a slightly complicated, but surprisingly high-quality path to neutron computed tomography images in 3D, but not a replacement for the even more powerful commercial software mentioned above. (C) 2017 The Authors. Published by Elsevier B.V.
The large volume of data and computational complexity of algorithms limit the application of hyperspectral image classification to real-time operations. This work addresses the use of different parallelprocessing tec...
详细信息
The large volume of data and computational complexity of algorithms limit the application of hyperspectral image classification to real-time operations. This work addresses the use of different parallelprocessing techniques to speed up the Markov random field (MRF)-based method to perform spectral-spatial classification of hyperspectral imagery. The Metropolis relaxation labelling approach is modified to take advantage of multi-core central processing units (CPUs) and to adapt it to massively parallelprocessingsystems like graphics processing units (GPUs). The experiments on different hyperspectral data sets revealed that the implementation approach has a huge impact on the execution time of the algorithm. The results demonstrated that the modified MRF algorithm produced classification accuracy similar to conventional methods with greatly improved computational performance. With modern multi-core CPUs, good computational speed-up can be achieved even without additional hardware support. The CPU-GPU hybrid framework rendered the otherwise computationally expensive approach suitable for time-constrained applications.
Advancements in medical imaging research are continuously providing doctors with better diagnostic information, removing the need for unnecessary surgeries and increasing accuracy in predicting life-threatening condit...
详细信息
Advancements in medical imaging research are continuously providing doctors with better diagnostic information, removing the need for unnecessary surgeries and increasing accuracy in predicting life-threatening conditions. However, newly developed techniques are currently limited by the capabilities of existing computer hardware, restricting them to expensive, custom-designed machines that only the largest hospital systems can afford or even worse, precluding them entirely. Many of these issues are due to existing hardware being ill-suited for these types of algorithms and not designed with medical imaging in mind.
In this thesis we discuss our efforts to motivate and democratize architectural support for advanced medical imaging tasks with MIRAQLE, a medical image reconstruction benchmark suite. In particular, MIRAQLE focuses on advanced image reconstruction techniques for 3D ultrasound, low-dose x-ray CT, and dynamic MRI. For each imaging modality we provide a detailed background and parallel implementations to enable future hardware development. In addition to providing baseline algorithms for these workloads, we also develop a unique analysis tool that provides image quality feedback for each simulation. This allows hardware designers to explore acceptable image quality trade-offs in algorithm-hardware co-design, potentially allowing for even more efficient solutions than hardware innovations alone could provide.
We also motivate the need for such tools by discussing Sonic Millip3De, our low-power, highly parallel hardware for 3D ultrasound. Using Sonic Millip3De, we illustrate the orders-of-magnitude power efficiency improvement that better medical imaging hardware can provide, especially when developed with a hardware-software co-design. We also show validation of the design using a scaled-down FPGA proof-of-concept and discuss our further refinement of the hardware to support a wider range of applications and produce higher frame rates. Overall, with
This paper provides details of both hardware and software conception and realization of a hand-held stereo embedded system for underwater imaging. The designed system can run most imageprocessing techniques smoothly ...
详细信息
This paper presents strategies to massively parallelize complete recursive systems. Each algorithm handles systems with feedforward and feedback coefficients allowing to compute high-complexity filtering operators. Th...
详细信息
This paper presents strategies to massively parallelize complete recursive systems. Each algorithm handles systems with feedforward and feedback coefficients allowing to compute high-complexity filtering operators. The final algorithm is linear in time and memory, exposes a high number of parallel tasks, and it is implemented on graphics processing units, i.e. GPUs. The key to the final algorithm is the derivation of closed-form formulas to combine both non-recursive and recursive linear filters, based on an efficient state-of-the-art block-based strategy. applications to early vision are considered in this work, hence the GPU implementation runs on images computing an approximation of the Gaussian filter and its first and second derivatives. Finally, comparison results are given showing that this work outperforms prior state-of-the-art algorithms, enabling it to achieve real-time image filtering on ultra-high-definition videos.
In this article, it is developed some area of issues related to data compression algorithms in the field of imageprocessing. imageprocessing area is very commonly used today with multiple applications in different f...
详细信息
ISBN:
(纸本)9781450347891
In this article, it is developed some area of issues related to data compression algorithms in the field of imageprocessing. imageprocessing area is very commonly used today with multiple applications in different fields, but also, the image compression methods or algorithms for imaging are used every day by the computer users. This paper will highlight the result of reports over the investigations or comparisons on image compression methods and will provide conclusions and ideas for further research in this area, with intense uses. Today there are a lot of different data compression methodologies, which are used to compress different data formats like, video, audio, image files. This article represents a comparison of several compression methods based on previous research and the analysis in the context of their current needs. In conclusion, this topic combines imageprocessingsystems, the advantage of using parallel programming, the benefits and results of the image compression and also the importance of some fundamental algorithms in this area.
In Part I of this paper, we proposed and analyzed a novel algorithmic framework for the minimization of a nonconvex objective function, subject to nonconvex constraints, based on inner convex approximations. This Part...
详细信息
A parallel 4D fMRI filtering algorithmis proposed to overcome the bottlenecks of large 4D volumetric fMRI data and its overlapping segments by input decimation, multidimensional intensive computation by parallel proce...
详细信息
A parallel 4D fMRI filtering algorithmis proposed to overcome the bottlenecks of large 4D volumetric fMRI data and its overlapping segments by input decimation, multidimensional intensive computation by parallelprocessing and the boundary conditions by output interpolation. Three spatial convolution architectures implement this parallel multidimensional filtering algorithm in Virtex-6 FPGA board, as automated 4D fMRI filtering systems. These three automated filtering systems are devised as "plug and develop" processors to filter any 4D volumetric data. Then, two sets of generic Edge and noise smoothing filtering operators are prototypically plugged and developed to be improved for filtering a dementia case study of color 256 x 256 x 4 x 3 volumetric fMRI. Accordingly, performance indices of the three architectures are evaluated as a complete package of area, speed, dynamic power, and throughput. Significant improvements have been achieved in keeping a stable speed, decreasing power consumption and increasing throughput in color fMRI filtering applications. All three architectures have an operating (225 MHz) maximum frequency. The power consumption improved more than two-fold using architecture 2 compared to 3. The highest throughput is achieved by architectures 2 and 3 almost (2.5) times than that of architecture 1. Evidently, all three architectures are performance-aware processors, and architecture 2 is optimal.
Due to the trade-offs between accuracy and speed, binocular stereo vision is still a challenging task in 3D computer vision research area. In this paper, an efficient stereo matching algorithm is implemented on a stat...
详细信息
Due to the trade-offs between accuracy and speed, binocular stereo vision is still a challenging task in 3D computer vision research area. In this paper, an efficient stereo matching algorithm is implemented on a state-of-the-art GPU to achieve highly accurate disparity maps in real time for various autonomous vehicle applications. The proposed algorithm is developed from our previous paper, where the search range at row v is propagated from three estimated neighbourhood disparities located at row v + 1. In order to speed up the execution, the prevalent NCC algorithm is optimised by factorising the equation into five independent parts. The computations of hi, H r , aj and a r are accelerated by using the integral images ii, Ir, 12 and I r 2. The values of h and a are stored in static program storage for indexing during the stereo matching, which further reduces expensive calculations to help the system perform in real time. The main purpose of this work is to accelerate the processing speed by highly exploiting the parallel computing architectures (OpenMP and CUDA). The performance of the implementation on an NVIDIA GTx 970M GPU is compared with the performance of the implementations on an Intel Core i7-4720HQ CPU using both single thread and multiple threads. The experimental results illustrate that the GPU implementation yields 37 fps when processing the images (resolution: 1242 × 375) from the KITTI database, which is between two and nine times faster than the implementations on the CPU using a different number of threads.
imageprocessingalgorithms, implemented in hardware, have recently emerged as the most viable solution for improving the performance of imageprocessingsystems. In this paper, a version of an anisotropic diffusion t...
详细信息
imageprocessingalgorithms, implemented in hardware, have recently emerged as the most viable solution for improving the performance of imageprocessingsystems. In this paper, a version of an anisotropic diffusion technique is used to reduce noise from retinal images, namely Speckle Reducing Anisotropic Diffusion ( SRAD). The SRAD filter can improve images corrupted by multiplicative or additive noise, but it has been the most computationally complex and it has not been suitable for software implementation in real-time processing. In this paper, an efficient Field-Programmable Gate Array ( FPGA)-based implementation of the SRAD filter is presented to accelerate the processing time. A comparison of the most used classical suppression filters like Gaussian, Median, Perona and Malik anisotropic diffusion has been carried out. The experimental results reveal a 38x performance improvement over the original MATLAB implementation and a 1.33x performance improvement over the hardware implementation using the xilinx System Generator tool.
暂无评论