• ETRI Journal
• /
• v.44 no.1
• /
• pp.62-72
• /
• 2022

In this study, we propose a multi-GPU-based 8KVR stitching system that operates in real time on both local and cloud machine environments. The proposed system first obtains multiple 4 K video inputs, decodes them, and generates a stitched 8KVR video stream in real time. The generated 8KVR video stream can be downloaded and rendered omnidirectionally in player apps on smartphones, tablets, and head-mounted displays. To speed up processing, we adopt group-of-pictures-based distributed decoding/encoding and buffering with the NV12 format, along with multi-GPU-based parallel processing. Furthermore, we develop several algorithms such as equirectangular projection-based color correction, real-time CG overlay, and object motion-based seam estimation and correction, to improve the stitching quality. From experiments in both local and cloud machine environments, we confirm the feasibility of the proposed 8KVR stitching system with stitching speed of up to 83.7 fps for six-channel and 62.7 fps for eight-channel inputs. In addition, in an 8KVR live streaming test on the 5G MEC/cloud, the proposed system achieves stable performances with 8 K@30 fps in both indoor and outdoor environments, even during motion.

• Annual Conference of KIPS
• /
• 2016.10a
• /
• pp.50-53
• /
• 2016

Image processing techniques play an increasingly important role in many aspects of our daily life. For example, it has been shown to improve agricultural productivity in a number of ways such as plant pest detecting or fruit grading. However, massive quantities of images generated in real-time through multi-devices such as remote sensors during monitoring plant growth lead to the challenges of big data. Meanwhile, most current image processing systems are designed for small-scale and local computation, and they do not scale well to handle big data problems with their large requirements for computational resources and storage. In this paper, we have proposed an IPABigData (Image Processing Algorithm BigData) platform which provides algorithms to support large-scale image processing in agriculture based on Hadoop framework. Hadoop provides a parallel computation model MapReduce and Hadoop distributed file system (HDFS) module. It can also handle parallel pipelines, which are frequently used in image processing. In our experiment, we show that our platform outperforms traditional system in a scenario of image segmentation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.5
• /
• pp.1004-1009
• /
• 2004

Precise time synchronization is a main technology in high-speed communications, parallel and distributed processing systems, Internet information industry and electronic commerce. Synchronized clocks are useful for many leasers. Often a distributed system is designed to realize some synchronized behavior, especially in real-time processing in factories, aircraft, space vehicles, and military applications. Nowadays, time synchronization has been compulsory thing as distributed processing and network operations are generalized. A network time server obtains, keeps accurate and precise time by synchronizing its local clock to standard reference time source and distributes time information through standard time synchronization protocol. This paper describes design issues and implementation of a network time server for time synchronization especially based on a clock model. The system uses GPS (Global Positioning System) as a standard reference time source and offers UTC (universal Time coordinated) through NTP (Network Time protocol). Implementation result and performance analysis are also presented.

• The Journal of the Korea Contents Association
• /
• v.12 no.10
• /
• pp.1-10
• /
• 2012

Many statistical methods have been adapted for terminology recognition to improve its accuracy. However, since previous studies have been carried out in a single core or a single machine, they have difficulties in real-time analysing explosively increasing documents. In this study, the task where bottlenecks occur in the process of terminology recognition is classified into linguistic processing in the process of 'candidate terminology extraction' and collection of statistical information in the process of 'terminology weight assignment'. A terminology recognition system is implemented and experimented to address each task by means of the distributed parallel processing-based MapReduce. The experiments were performed in two ways; the first experiment result revealed that distributed parallel processing by means of 12 nodes improves processing speed by 11.27 times as compared to the case of using a single machine and the second experiment was carried out on 1) default environment, 2) multiple reducers, 3) combiner, and 4) the combination of 2)and 3), and the use of 3) showed the best performance. Our terminology recognition system contributes to speed up knowledge extraction of large scale science and technology documents.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.10
• /
• pp.2180-2188
• /
• 2009

This paper is study on real-time hand gesture recognition system based on vision for intelligent robot control. We are proposed a recognition system using PCA and BP algorithm. Recognition of hand gestures consists of two steps which are preprocessing step using PCA algorithm and classification step using BP algorithm. The PCA algorithm is a technique used to reduce multidimensional data sets to lower dimensions for effective analysis. In our simulation, the PCA is applied to calculate feature projection vectors for the image of a given hand. The BP algorithm is capable of doing parallel distributed processing and expedite processing since it take parallel structure. The BP algorithm recognized in real time hand gestures by self learning of trained eigen hand gesture. The proposed PCA and BP algorithm show improvement on the recognition compared to PCA algorithm.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.640-643
• /
• 2003

A Walsh function based associative memory is capable of storing m patterns in a single pattern storage space with Walsh encoding of each pattern. Furthermore, each stored pattern can be matched against the stored patterns extremely fast using algorithmic parallel processing. As such, this special type of memory is ideal for real-time processing of large scale information. However this incredible efficiency generates large amount of crosstalk between stored patterns that incurs mis-recognition. This crosstalk is a function of the set of different sequencies [number of zero crossings] of the Walsh function associated with each pattern to be stored. This sequency set is thus optimized in this paper to minimize mis-recognition, as well as to maximize memory saying. In this paper, this Walsh memory has been applied to the problem of face recognition, where PCA is applied to dimensionality reduction. The maximum Walsh spectral component and genetic algorithm (GA) are applied to determine the optimal Walsh function set to be associated with the data to be stored. The experimental results indicate that the proposed methods provide a novel and robust technology to achieve an error-free, real-time, and memory-saving recognition of large scale patterns.

• The Journal of Information Technology
• /
• v.2 no.2
• /
• pp.145-161
• /
• 1999

This paper proposes a high speed back propagation neural networks which uses the residue number system. making the high speed operation possible without carry propagation Consisting of MAC(Multiplication and Accumulation) operator unit using Residue number system and sigmoid function operator unit using Mixed Residue Conversion is designed, The Designed circuits are descripted by VHDL and synthesized by Compass tools. Result of simulations shows that critical path delay time is about 19nsec and the size can be reduced to 40% compared to the neural networks implemented by the real number operation unit. The proposed design circuits can be implemented in parallel distributed processing system with desired real time processing.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.4
• /
• pp.289-293
• /
• 2016

As more mobile devices are equipped with multi-core CPUs and are required to execute many compute-intensive multimedia applications, it is important to optimize the systems, considering the underlying parallel hardware architecture. In this paper, we implement and optimize ray-tracing application tailored to a given mobile computing platform with multiple heterogeneous processing elements. In this paper, a lightweight ray-tracing application is specified and implemented in Kahn process network (KPN) model-of-computation, which is known to be suitable for the description of real-time applications. We take an open-source C/C++ implementation of ray-tracing and adapt it to KPN description in the Distributed Application Layer framework. Then, several possible configurations are evaluated in the target mobile computing platform (Exynos 5422), where eight heterogeneous ARM cores are integrated. We derive the optimal degree of parallelism and a suitable distribution of the replicated tasks tailored to the target architecture.

• Journal of KIISE:Computing Practices and Letters
• /
• v.5 no.6
• /
• pp.700-707
• /
• 1999

본 논문에서는 GIS 관련 연산을 실시간에 효율적으로 처리하기 위한 분산공유메모리 기반 병렬처리 시스템을 제안한다. 본 논문의 분산공유메모리 시스템은 메시지전달 방식의 분산메모리 MIMD 컴퓨터 상에 소프트웨어 기반 분산공유메모리 모듈을 탑재함으로써 구현되었다. 또한 GIS 연산의 기본이 되는 공간 객체를 공유의 기본 단위로 설정하고, GIS 데이타의 특성을 반영하여 읽기전용 공유데이타 타입을 추가하였으며, 네트워크 오버헤드를 줄이기 위하여 복수의 객체를 한번에 읽어오는 bulk access가 가능하도록 하였다. 본 시스템에서는 GIS 데이타의 효율적인 분배를 위하여 부하균등화 기법으로 guided self scheduling을 사용하였다. 실험결과 본 시스템은 네트워크 캐쉬의 효율적인 활용을 통하여 소프트웨어 기반 분산메모리 시스템의 오버헤드에도 불구하고 MPI 기반 메시지전달 방식에 비하여 향상된 성능을 얻을 수 있었다.Abstract In this paper, we propose a distributed shared memory(DSM) based parallel processing system to process GIS related computations efficiently in real time. The system is based on a software DSM module implemented on top of a distributed MIMD computer. In the DSM system, spatial object, which is a fundamental structure to represent GIS data, is used as a basic unit for sharing, and a read-only shared data type is added to reflect the characteristics of GIS data. In addition, a bulk access to multiple shared data is made possible to reduce the network overhead. A guided self scheduling method is devised for efficient load balancing in distributing GIS data to parallel processors. The experimental results show that the DSM system performs better than an MPI based message-passing system through the efficient utilization of network cache in spite of the system's software overhead.

• KIISE Transactions on Computing Practices
• /
• v.21 no.8
• /
• pp.561-566
• /
• 2015

Hadoop is becoming widely adopted in scientific and commercial areas as an open-source distributed data processing framework. Recently, for real-time processing and analysis of data, an attempt to apply high-performance computing technologies to Hadoop is being made. In this paper, we have expanded the Hadoop Filesystem library to support Lustre, which is a popular high-performance parallel distributed filesystem, and implemented the Hadoop MapReduce execution environment over the Lustre filesystem. We analysed Hadoop MapReduce over Lustre by using Hadoop standard benchmark tools. We found that Hadoop MapReduce over Lustre execution has a performance 2-13 times better than a typical Hadoop MapReduce execution.