A parallel method for impulsive image noise removal on hybrid CPU/GPU systems

A parallel algorithm for image noise removal is proposed. The algorithm is based on peer group concept and uses a fuzzy metric. An optimization study on the use of the CUDA platform to remove impulsive noise using this algorithm is presented. Moreover, an implementation of the algorithm on multi-core platforms using OpenMP is presented. Performance is evaluated in terms of execution time and a comparison of the implementation parallelised in multi-core, GPUs and the combination of both is conducted. A performance analysis with large images is conducted in order to identify the amount of pixels to allocate in the CPU and GPU. The observed time shows that both devices must have work to do, leaving the most to the GPU. Results show that parallel implementations of denoising filters on GPUs and multi-cores are very advisable, and they open the door to use such algorithms for real-time processing.

Parallel Computational Intelligence-Based Multi-Camera Surveillance System

In this work, we present a multi-camera surveillance system based on the use of self-organizing neural networks to represent events on video. The system processes several tasks in parallel using GPUs (graphic processor units). It addresses multiple vision tasks at various levels, such as segmentation, representation or characterization, analysis and monitoring of the movement. These features allow the construction of a robust representation of the environment and interpret the behavior of mobile agents in the scene. It is also necessary to integrate the vision module into a global system that operates in a complex environment by receiving images from multiple acquisition devices at video frequency. Offering relevant information to higher level systems, monitoring and making decisions in real time, it must accomplish a set of requirements, such as: time constraints, high availability, robustness, high processing speed and re-configurability. We have built a system able to represent and analyze the motion in video acquired by a multi-camera network and to process multi-source data in parallel on a multi-GPU architecture.

Parallel relaxed and extrapolated algorithms for computing PageRank

In this paper, parallel Relaxed and Extrapolated algorithms based on the Power method for accelerating the PageRank computation are presented. Different parallel implementations of the Power method and the proposed variants are analyzed using different data distribution strategies. The reported experiments show the behavior and effectiveness of the designed algorithms for realistic test data using either OpenMP, MPI or an hybrid OpenMP/MPI approach to exploit the benefits of shared memory inside the nodes of current SMP supercomputers.

Geometric 3D point cloud compression

The use of 3D data in mobile robotics applications provides valuable information about the robot’s environment but usually the huge amount of 3D information is unmanageable by the robot storage and computing capabilities. A data compression is necessary to store and manage this information but preserving as much information as possible. In this paper, we propose a 3D lossy compression system based on plane extraction which represent the points of each scene plane as a Delaunay triangulation and a set of points/area information. The compression system can be customized to achieve different data compression or accuracy ratios. It also supports a color segmentation stage to preserve original scene color information and provides a realistic scene reconstruction. The design of the method provides a fast scene reconstruction useful for further visualization or processing tasks.

Adjustable compression method for still JPEG images

There are a large number of image processing applications that work with different performance requirements and available resources. Recent advances in image compression focus on reducing image size and processing time, but offer no real-time solutions for providing time/quality flexibility of the resulting image, such as using them to transmit the image contents of web pages. In this paper we propose a method for encoding still images based on the JPEG standard that allows the compression/decompression time cost and image quality to be adjusted to the needs of each application and to the bandwidth conditions of the network. The real-time control is based on a collection of adjustable parameters relating both to aspects of implementation and to the hardware with which the algorithm is processed. The proposed encoding system is evaluated in terms of compression ratio, processing delay and quality of the compressed image when compared with the standard method.

3DCOMET: 3D compression methods test dataset

The use of 3D data in mobile robotics applications provides valuable information about the robot’s environment. However usually the huge amount of 3D information is difficult to manage due to the fact that the robot storage system and computing capabilities are insufficient. Therefore, a data compression method is necessary to store and process this information while preserving as much information as possible. A few methods have been proposed to compress 3D information. Nevertheless, there does not exist a consistent public benchmark for comparing the results (compression level, distance reconstructed error, etc.) obtained with different methods. In this paper, we propose a dataset composed of a set of 3D point clouds with different structure and texture variability to evaluate the results obtained from 3D data compression methods. We also provide useful tools for comparing compression methods, using as a baseline the results obtained by existing relevant compression methods.

An illustrated flora of the northern United States, Canada and the British possessions, from Newfoundland to the parallel of the southern boundary of Virginia, and from the Atlantic Ocean westward to the 102d meridian, by Nathaniel Lord Britton ... and Hon. Addison Brown ...

v. 1

A parallel currency for Greece. CEPS High-level Brief, 20 May 2015

Greece and its creditors seem to be engaged in a game of chicken: both sides expect the other to yield at the last moment. The game will almost certainly end with each side deviating somewhat from its preferred course. This High-Level Brief discusses how a parallel currency could contribute to a resolution of the conflict. In the author's view, it would be the least-bad option for both sides among three possible options on the table.

Compression Loading Induced Cellular Stress Response of Intervertebral Disc Cells in Organ Culture

Introduction: Mechanical stress is often associated to interverterbal disc (IVD) degeneration and the effect of mechanical loading on IVD has been studied and reviewed.1,2 Previously, expression of heat shock proteins, HSP70 and HSP27 has been found in pathological discs.3 However, there is no direct evidence on whether IVD cells respond to the mechanical loading by expression of HSPs. The objective of this study is to investigate the stress response of IVD cells during compressive loading in an organ culture. Materials and Methods: Fresh adult bovine caudal discs were cultured with compressive loading applied at physiological range. Effect of loading type (static and dynamic) and repeated loading (2 hours per day for 2 days) were studied. Nucleus pulposus (NP) and annulus fibrosus (AF) of the IVD were retrieved at different time points: right after loading and right after resting. Positive control discs were heat shocked (43°C). Cell activity was assessed and expression of stress response genes (HSP70 and HSF1) and matrix remodeling genes (ACAN, COL2, COL1, ADAMTS4, MMP3 and MMP13) were studied. Results: Cell activity was maintained in all groups. Both NP and AF expressed high level of HSP70 in heat shock groups, confirming their expression in response to stress. In NP, expression of HSP70 was up-regulated after static loading and dynamic loading with higher fold change was observed after static loading. During repeated loading, HSP70 appeared to be upregulated right after loading and decreased after resting. Such trend was not observed in AF and HSF1 levels. Expressions of matrix remodeling genes did not change significantly with loading except ADAMTS4 decreased in AF during static loading. Conclusion: This study demonstrated that NP cells upregulate expression of HSP70 in response to loading induced stress without changing cell activity and matrix remodeling significantly. Acknowledgments: This project was funded by AO Spine (AOSPN) (grant number: SRN_2011_14) and a fellowship exchange award by AO Spine Scientific Research Network (SRN).

Structural features in ODP Holes 128-794D and 128-799B

Numerous structural features occur in the Leg 128 cores from the Japan Sea. They include (1) gravity-induced structures such as slump folds, (2) dewatering structures comprising several sets of veins, and (3) larger faults and veins developed in the volcanic basement of the Yamato Basin as well as in the sedimentary rocks of the Oki Ridge and Kita-Yamato Trough. Gravity-induced structures, mainly slumps and associated faults, suggest the existence of paleoslopes and the dominance of gravitational tectonics during the early and middle Miocene, at the Pliocene/Pleistocene boundary, and during the Quaternary. Several types of mud-filled veins having various shapes were observed. These are especially abundant in the middle Miocene siliceous claystones and porcellanites from the Kita-Yamato Trough. They have been interpreted as dewatering conduits that formed preferentially in highly porous, water-saturated diatomaceous muds on a slope, because of episodic loss of sediment strength, collapse of the sediment framework, and consequent fluid migration. The central part of the vein serves once as a fluid conduit, whereas the transition between conduit-controlled and intergranular flow occurs at the branching extremities, with concentration of fines. The likely trigger responsible for the strength loss is seismic activity. Development of these veins, spatially and chronologically linked to small normal microfaults, implies an extensional regime having layer-parallel extension and a local bedding-parallel shear couple, probably the result of gravitational gliding. The brittle fractures found in Yamato Basin basement Hole 794D cores comprise joints, faults, and veins filled with chlorite-saponite, saponite, and calcite. They suggest a likely transpressive to transtensional regime around the early Miocene/ middle Miocene boundary, with a north-northeast-south-southwest compression alternating with a west-northwest-eastsoutheast extension. The faults from Site 799 cores on the Yamato Rise exhibit a prominent early Miocene-middle Miocene extensional environment, a late Miocene-early Pliocene phase of normal and strike-slip faulting, and a final phase that began during the latest Pliocene. Site 798, on the Oki Ridge, reveals faults that recorded a consistent extensional tectonic regime from Pliocene to the Holocene. These data support the pull-apart kinematic model for early Miocene-middle Miocene time, as regarding the stress regime deduced from the Yamato Basin basement fractures. The recent compression known in the eastern margin of the Japan Sea was not documented by compressive structures at any site. The late Miocene-early Pliocene faulting phase corresponds to a major and general reorganization of the stress distribution in the arc area. Evidence for rapid and main subsidence and synsedimentary extension of the Yamato Basin and Yamato Rise areas between 20 and 15 Ma, and the concomitant rotation of southwest Japan, raise the question of links between this opening and the Shimanto Belt collision in southwest Japan, between the arc and the Philippine Sea Plate.