RESEARCH ON SATELLITE IMAGE PROCESSING AND RECOGNITION WITH PARALLEL ALGORITHM

Using the method of mathematical morphology,this paper fulfills filtration,segmentation and extraction of morphological features of the satellite cloud image.It also gives out the relative algorithms,which is realized by parallel C programming based on Transputer networks.It has been successfully used to process the typhoon and the low tornado cloud image.And it will be used in weather forecast.

Parallel Processing Based on Ship Maneuvering in Identification of Interaction Force Coefficients

The parallel processing based on the free running model test was adopted to predict the interaction force coefficients （flow straightening coefficient and wake fraction） of ship maneuvering. And the multipopulation genetic algorithm （MPGA） based on real coding that can contemporarily process the data of free running model and simulation of ship maneuvering was applied to solve the problem. Accordingly the optimal individual was obtained using the method of genetic algorithm. The parallel processing of multiopulation solved the prematurity in the identification for single population, meanwhile, the parallel processing of the data of ship maneuvering （turning motion and zigzag motion） is an attempt to solve the coefficient drift problem. In order to validate the method, the interaction force coefficients were verified by the procedure and these coefficients measured were compared with those ones identified. The maximum error is less than 5%, and the identification is an effective method.

Parallel Image Processing Technology of Surface Detection System

To improve image processing speed and detection precision of a surface detection system on a strip surface,based on the analysis of the characteristics of image data and image processing in detection system on the strip surface,the design of parallel image processing system and the methods of algorithm implementation have been studied. By using field programmable gate array(FPGA) as hardware platform of implementation and considering the characteristic of detection system on the strip surface,a parallel image processing system implemented by using multi IP kernel is designed. According to different computing tasks and the load balancing capability of parallel processing system,the system could set different calculating numbers of nodes to meet the system's demand and save the hardware cost.

A Survey of MapReduce Based Parallel Processing Technologies

Along with the increasing Big Data challenges, the MapReduce based systems are extensively welcomed, because of their remarkable simplicity and scalability. However, from the first day MapReduce is proposed, its argument with parallel Dt3MSs never stops, as it over-focuses on the scalability but overlooks the efficiency. Accordingly, extended systems are proposed in order to improve the peDbrmance on the limited scale clusters. In the meantime, traditional RDBMS technologies like structured data model, transaction, SQL, etc. are also getting more attention. This paper reviews such systems, from Google and also the third parties, trying to indicate the directions for the future research.

REALIZATION OF QUICK-LOOK IMAGING FOR SPACEBORNE SAR BASED ON PARALLEL PROCESSING

Large range cell migration is a severe challenge to imaging algorithm for spaceborne SAR. Based on design of Finite Impulse Response (FIR) filter and Range Doppler (RD) algorithm, a realization of quick-look imaging for large range cell migration is proposed. It realized quick-look imaging of 8 times reduced resolution with parallel processing on memory shared 8 CPU SGI server. According to simulation experiment, this quick-look imaging algorithm with parallel processing can image 16384x16384 SAR raw data within 6 seconds. It reaches the requirement of real-time imaging.

Using Graphics Processing Units to Parallelize the FDK Algorithm for Tomographic Image Reconstruction

The paper presents the implementation of a parallel version of FDK （Felkamp, David e Kress） algorithm using graphics processing units. Discussion was briefly some elements the computed tomographic scan and FDK algorithm; and some ideas about GPUs （Graphics Processing Units） and its use in general purpose computing were presented. The paper shows a computational implementation of FDK algorithm and the process of parallelization of this implementation. Compare the parallel version of the algorithm with the sequential version, used speedup as a performance metric. To evaluate the performance of parallel version, two GPUs, GeForce 9400GT （16 cores） a low capacity GPU and Quadro 2000 （192 cores） a medium capacity GPU was reached speedup of 3.37.

Fourier hologram method using Gerchberg-Saxton algorithm for parallel femtosecond laser processing

In order to improve femtosecond laser throughput,a parallel processing system consisting of liquid crystal on silicon(LCOS)device as spatial light modulator is put forward.A method is described for displaying Fourier hologram on LCOS,and a high uniformity of several diffraction peaks in the computer reconstruction is achieved.Application of this method to the parallel femtosecond laser processing is also demonstrated,and two intersecting rings and three tangent rings are fabricated respectively by one time in the photoresist.

Parallel Processing Design for LTE PUSCH Demodulation and Decoding Based on Multi-Core Processor

The Long Term Evolution (LTE) system imposes high requirements for dispatching delay.Moreover,very large air interface rate of LTE requires good processing capability for the devices processing the baseband signals.Consequently,the single-core processor cannot meet the requirements of LTE system.This paper analyzes how to use multi-core processors to achieve parallel processing of uplink demodulation and decoding in LTE systems and designs an approach to parallel processing.The test results prove that this approach works quite well.

Efficient Parallel Processing of k-Nearest Neighbor Queries by Using a Centroid-based and Hierarchical Clustering Algorithm

The k-Nearest Neighbor method is one of the most popular techniques for both classification and regression purposes.Because of its operation,the application of this classification may be limited to problems with a certain number of instances,particularly,when run time is a consideration.However,the classification of large amounts of data has become a fundamental task in many real-world applications.It is logical to scale the k-Nearest Neighbor method to large scale datasets.This paper proposes a new k-Nearest Neighbor classification method(KNN-CCL)which uses a parallel centroid-based and hierarchical clustering algorithm to separate the sample of training dataset into multiple parts.The introduced clustering algorithm uses four stages of successive refinements and generates high quality clusters.The k-Nearest Neighbor approach subsequently makes use of them to predict the test datasets.Finally,sets of experiments are conducted on the UCI datasets.The experimental results confirm that the proposed k-Nearest Neighbor classification method performs well with regard to classification accuracy and performance.

Improved Strategies for Parallel Medical Image Processing Applications

In order to meet the demands of high efficient and real-time computer assisted diagnosis as well as screening in medical area, to improve the efficacy of parallel medical image processing is of great importance. This article proposes improved strategies for parallel medical image processing applications,which is categorized into two genera. For each genus individual strategy is devised, including the theoretic algorithm for minimizing the exertion time. Experiment using mammograms not only justifies the validity of the theoretic analysis, with reasonable difference between the theoretic and measured value, but also shows that when adopting the improved strategies, efficacy of medical image parallel processing is improved greatly.

PARALLEL REGION PRESERVING MULTISECTION METHOD FOR SOLVING GENERALIZED EIGENPROBLEM

The parallel multisection method for solving algebraic eigenproblem has been presented in recent years with the development of the parallel computers, but all the research work is limited in standard eigenproblems of symmetric tridiagonal matrix. The multisection method for solving the generalized eigenproblem applied significantly in many science and engineering domains has not been studied. The parallel region preserving multisection method (PRM for short) for solving generalized eigenproblems of large sparse and real symmetric matrix is presented in this paper. This method not only retains the advantages of the conventional determinant search method (DS for short), but also overcomes its disadvantages such as leaking roots and disconvergence. We have tested the method on the YH 1 vector computer, and compared it with the parallel region preserving determinant search method the parallel region preserving bisection method (PRB for short). The numerical results show that PRM has a higher speed up, for instance, it attains the speed up of 7.7 when the scale of the problem is 2 114 and the eigenpair found is 3, and PRM is superior to PRB when the scale of the problem is large.

Application of TMS320C80 in Image Processing

To study the application of TMS320C80 in image processing, an image processing system was designed based on this device, and the task of real time image processing was well accomplished on the hardware platform. TMS320C80 architecture's high degree of on chip integration and software flexibility will make it widely used in image processing that requires high processing speeds.

Operation of three parallel AN/AO processes to enrich denitrifying phosphorus removing bacteria for low strength wastewater treatment

Three parallel anaerobic-anoxic/anaerobic-aerobic （AN/AO） processes were developed to enrich denitrifying phosphorus removal bacteria （DPB） for low strength wastewater treatment. The main body of the parallel AN/AO process consists of an AN （anaerobic-anoxic） process and an AO （anaerobic-aerobic） process. In the AO process, the common phosphorus accumulating organisms （PAOs） was dominate, while in the AN process, DPB was dominate, The volume of anaerobic zone（Vana）：anoxie zone（Vano） ： aerobic zone （Vaer） for the parallel AN/AO process is 1：1：1 in contrast with a Vana：Vaer and Vano：Vaer of 1：2 and 1：4 for a traditional biological nutrient removal process （BNR）. Process 3 excels in the 3 processes on the basis of COD, TN and TP removal. For 4 month operation, the effluent COD concentration of process 3 did not exceed 60 mg/L; the effluent TN concentration of process 3 was lower than 15 mg/L; and the effluent TP concentration of process 3 was lower than 1 mg/L.

On the Communication-Efficiency of Parallel Systems

This peper defines the communication-efficiency, which is directly related to the cost-efficiency, and Studies the relationship between the communication-efficiency and the processor-efficiency when they are applied to scalability analysis. An example of algorithms is given to analyze some typical architectures.

Assigning Task by Parallel Genetic Algorithm Based on PVM

Genetic algorithm has been proposed to solve the problem of task assignment. However, it has some drawbacks, e.g., it often takes a long time to find an optimal solution, and the success rate is low. To overcome these problems, a new coarse grained parallel genetic algorithm with the scheme of central migration is presented, which exploits isolated sub populations. The new approach has been implemented in the PVM environment and has been evaluated on a workstation network for solving the task assignment problem. The results show that it not only significantly improves the result quality but also increases the speed for getting best solution.

AN IMPROVED RECURSIVE DOUBLING ALGORITHM FOR THE PARALLEL SOLUTION OF LINEAR RECURRENCE R

An improved recursive doubling algorithm for solving linear recurrence R <n,1>is given,whose parallel time complexity is (τ++τ.) logn when n processors are available,achieving the lower bound in array processor type computation.

The inversion of density structure by graphic processing unit(GPU) and identification of igneous rocks in Xisha area

Organic reefs, the targets of deep-water petro- leum exploration, developed widely in Xisha area. However, there are concealed igneous rocks undersea, to which organic rocks have nearly equal wave impedance. So the igneous rocks have become interference for future explo- ration by having similar seismic reflection characteristics. Yet, the density and magnetism of organic reefs are very different from igneous rocks. It has obvious advantages to identify organic reefs and igneous rocks by gravity and magnetic data. At first, frequency decomposition was applied to the free-air gravity anomaly in Xisha area to obtain the 2D subdivision of the gravity anomaly and magnetic anomaly in the vertical direction. Thus, the dis- tribution of igneous rocks in the horizontal direction can be acquired according to high-frequency field, low-frequency field, and its physical properties. Then, 3D forward model- ing of gravitational field was carried out to establish the density model of this area by reference to physical properties of rocks based on former researches. Furthermore, 3D inversion of gravity anomaly by genetic algorithm method of the graphic processing unit （GPU） parallel processing in Xisha target area was applied, and 3D density structure of this area was obtained. By this way, we can confine the igneous rocks to the certain depth according to the density of the igneous rocks. The frequency decomposition and 3D inversion of gravity anomaly by genetic algorithm method of the GPU parallel processing proved to be a useful method for recognizing igneous rocks to its 3D geological position. So organic reefs and igneous rocks can be identified, which provide a prescient information for further exploration.

APPLICATION OF MVP IN REAL TIME IMAGE PROCESSING

MVP is a digital signal processor, which is of MIMD structure and fit for multimedia application. MVP has several processors in it, and its operation is characteristic of parallelism and pipeline; therefore, real-time signal processing can be done on it. This paper presents the image processing system based on MVP, explains the principles of parallel task assignment and hardware pipeline design, and gives out the example of target tracking and edge detection.

A Granularity-Aware Parallel Aggregation Method for Data Streams

This paper focuses on the parallel aggregation processing of data streams based on the shared-nothing architecture. A novel granularity-aware parallel aggregating model is proposed. It employs parallel sampling and linear regression to describe the characteristics of the data quantity in the query window in order to determine the partition granularity of tuples, and utilizes equal depth histogram to implement partitio ning. This method can avoid data skew and reduce communi cation cost. The experiment results on both synthetic data and actual data prove that the proposed method is efficient, practical and suitable for time-varying data streams processing.