• 전기전자학회논문지
• /
• 제20권3호
• /
• pp.209-219
• /
• 2016

영상처리에 쓰이는 기계학습 방법 중 하나인 SVM은 일반화 능력이 뛰어나 객체를 분류하는 성능이 뛰어나다. SVM을 이용하여 객체를 분류하기 위해서는 여러 번의 MAC 연산을 반복해서 수행해야 한다. 하지만 영상의 해상도가 늘어남에 따라 분류를 해야 하는 개체가 늘어나게 되면 연산 시간이 증가하게 되어 실시간 처리를 요하는 고속 시스템에 사용하기 어렵다. 본 논문에서는 실시간 처리를 요하는 고속 시스템에서도 사용이 가능한 SVM 분류기 하드웨어 구조를 제안한다. 실시간 처리를 하는데 제한 요소가 되는 반복 연산은 병렬처리를 통하여 동시에 계산할 수 있게 하였고 다양한 종류의 특징점 추출기와도 호환이 가능하도록 설계하였다. 하드웨어 구현에 사용한 커널은 RBF 커널이며 커널 사용으로 생기는 지수 연산은 식을 변형하여 고정소수점 연산이 가능하도록 하였다. 제안한 하드웨어의 성능을 확인하기 위해 Xilinx ZC706 보드에 구현하였고 $1360{\times}800$ 해상도 이미지에 대한 수행 시간은 동작 주파수 100 MHz에서 약 60.46 fps로 실시간 처리가 가능함을 확인했다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권11호
• /
• pp.2827-2848
• /
• 2012

Previously, we described a social media cloud computing service environment (SMCCSE). This SMCCSE supports the development of social networking services (SNSs) that include audio, image, and video formats. A social media cloud computing PaaS platform, a core component in a SMCCSE, processes large amounts of social media in a parallel and distributed manner for supporting a reliable SNS. Here, we propose a Hadoop-based multimedia system for image and video transcoding processing, necessary functions of our PaaS platform. Our system consists of two modules, including an image transcoding module and a video transcoding module. We also design and implement the system by using a MapReduce framework running on a Hadoop Distributed File System (HDFS) and the media processing libraries Xuggler and JAI. In this way, our system exponentially reduces the encoding time for transcoding large amounts of image and video files into specific formats depending on user-requested options (such as resolution, bit rate, and frame rate). In order to evaluate system performance, we measure the total image and video transcoding time for image and video data sets, respectively, under various experimental conditions. In addition, we compare the video transcoding performance of our cloud-based approach with that of the traditional frame-level parallel processing-based approach. Based on experiments performed on a 28-node cluster, the proposed Hadoop-based multimedia transcoding system delivers excellent speed and quality.

• 천문학회지
• /
• 제47권2호
• /
• pp.43-47
• /
• 2014

Many advanced ground-based solar telescopes improve the spatial resolution of observation images using an adaptive optics (AO) system. As any AO correction remains only partial, it is necessary to use post-processing image reconstruction techniques such as speckle masking or shift-and-add (SAA) to reconstruct a high-spatial-resolution image from atmospherically degraded solar images. In the New Vacuum Solar Telescope (NVST), the spatial resolution in solar images is improved by frame selection and SAA. In order to overcome the burden of massive speckle data processing, we investigate the possibility of using the speckle reconstruction program in a real-time application at the telescope site. The code has been written in the C programming language and optimized for parallel processing in a multi-processor environment. We analyze the scalability of the code to identify possible bottlenecks, and we conclude that the presented code is capable of being run in real-time reconstruction applications at NVST and future large aperture solar telescopes if care is taken that the multi-processor environment has low latencies between the computation nodes.

• 한국방사선학회논문지
• /
• 제8권6호
• /
• pp.357-364
• /
• 2014

전산화단층촬영장치의 영상재구성방법으로 필터보정역투영법이 광범위하게 사용되고 있다. 평행빔과 부채살빔의 재구성에 사용되는 투영에 잡음이 포함되었을 때 재구성 된 영상의 잡음을 살펴보았다. 평행빔과 부채살 구조에서 각각 360개, 720개의 투영으로 $512{\times}512$ 크기로 Visual C++을 이용하여 영상재구성하였고, 원본 Shepp-Logan 두부 모형을 매우 잘 복원한다는 것을 확인하였다. 필터보정역투영법의 현실적인 접근(유한한 투영 개수)으로 인해 입력 잡음이 없어도 영상재구성 과정에서 잡음이 발생하였다. 입력 잡음비 0.5% 이하에서 잡음이 빠르게 증가하기 때문에 CT 장치의 잡음 제거 기술 및 영상처리 기법의 개발이 필요할 것이다.

• 동력기계공학회지
• /
• 제10권4호
• /
• pp.139-146
• /
• 2006

In this paper vector code correlation(VCC) method and an algorithm to promote the image processing performance in building an effective measurement system using cameras are described for automatically berthing and controlling the ship equipped with side thrusters. In order to realize automatic ship berthing, it is indispensable that the berthing assistant system on the ship should continuously trace a target in the berth to measure the distance to the target and the ship attitude, such that we can make the ship move to the specified location. The considered system is made up of 4 apparatuses compounded from a CCD camera, a camera direction controller, a popular PC with a built in image processing board and a signal conversion unit connected to parallel port of the PC. The object of this paper is to reduce the image processing time so that the berthing system is able to ensure the safety schedule against risks during approaching to the berth. It could be achieved by composing the vector code image to utilize the gradient of an approximated plane found with the brightness of pixels forming a certain region in an image and verifying the effectiveness on a commonly used PC. From experimental results, it is clear that the proposed method can be applied to the measurement system for automatic ship berthing and has the image processing time of fourfold as compared with the typical template matching method.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.54-57
• /
• 2003

In this paper, we propose an algorithm extracting character regions from scenery images. This algorithm works under a severe constraint: each pixel of a result image must be derived from only information of their neighbor pixels. This constraint is very important for a low cost device like a mobile camera. The proposed algorithm is represented by the local and parallel image processing. It has been tested for 100 scenery images. A result shows that the proposed algorithm can extract character regions at a rate of more than 90％. The result was obtained without learning any template images. the algorithm is very useful.

• 한국항행학회논문지
• /
• 제21권5호
• /
• pp.485-490
• /
• 2017

본 논문에서는 그래픽 프로세서를 이용하여 고속으로 해무를 제거하는 기술을 제안한다. 이 기술은 호스트 프로세서(CPU)와 병렬처리가 가능한 여러 개의 그래픽 프로세서를 이용하여 입력영상에서 해무를 제거하는 것이다. 해무를 제거하는 과정 중에서 다크 채널 추출, 최대 밝기 채널 추출, 전달량 계산은 호스트 프로세서에서 수행하고, 양방향 필터를 적용하여 전달량을 정제하는 과정을 그래픽 프로세서를 기반으로 병렬처리하여 연산속도를 높였다. 제안한 병렬처리 기법의 검증을 위해 NVIDIA사의 GTX 1070 GPU를 3개를 사용하여 검증환경을 구성하였다. 구현결과 하나의 그래픽 프로세서로 구현하였을 때는 평균 140ms가 소요되고, OpenMP와 다중 GPGPU를 이용하여 구현하였을 때 26ms 소요되었다. 본 논문에서 제안하는 그래픽 프로세서 기반의 병렬연산 해무제거 기술은 선박의 안전항해, 항만 관제 분야에 사용될 수 있을 것이다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.1101-1104
• /
• 1998

The modern multimedia applications which are video processor, video conference or video phone and so forth require real time processing. Because of a large amount of image data, those require high compression performance. In this paper, the prosposed image processing encoder was designed by using wavelet transform encoding. The proposed filter block can process imae data on the high speed because of composing individual function blocks by parallel and compute both highpass and lowpass coefficient in the same clock cycle. When image data is decomposed into multiresolution, the proposed scheme needs external memory and controller to save intermediate results and it can operate within 33MHz.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 II
• /
• pp.1137-1140
• /
• 2003

The area of the prototype device is less than 80mm$^2$. Operating with a 60ns clock cycle, the device typically dissipates only 300mW. The full functionality was proven by using the methodical test programs based on typical image processing operations. Also, we realized the whole process from conventional gray image to color image. Format converters, implemented using multidimensional access memories, transfer the data between the processing element array and conventional bit-parallel components in real time. The completed system is fully functional and performs typical low-level image processing tasks at speed exceeding 30 frames of traditional TV system per second.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2001년도 추계학술발표논문집 (상)
• /
• pp.767-770
• /
• 2001

Edge detection is one of issues with essential importance in the area of image process. An edge in image is a boundary or contour which a significant change occurs in image intensity. In the paper, we process edge detection algorithms which are based on Potts automata. The dynamical behavior of these automata is completely determined by Lyapunov operators for sequential and parallel update. If Potts Automata convergence to fixed points, then it can be used to image processing. From the generalized Potts automata point of view, we propose a Potts Automata technique for detecting edge. Based on the experimental results we discuss the advantage and efficiency.