• 제어로봇시스템학회논문지
• /
• 제15권8호
• /
• pp.778-785
• /
• 2009

This paper presents a Gabor texture feature extraction method for classification of discolored Metal pad images using GPU(Graphics Processing Unit). The proposed algorithm extracts the texture information using Gabor filters and constructs a pattern map using the extracted information. Finally, the golden pad images are classified by utilizing the feature vectors which are extracted from the constructed pattern map. In order to evaluate the performance of the Gabor texture feature extraction algorithm based on GPU, a sequential processing and parallel processing using OpenMP in CPU of this algorithm were adopted. Also, the proposed algorithm was implemented by using Global memory and Shared memory in GPU. The experimental results were demonstrated that the method using Shared memory in GPU provides the best performance. For evaluating the effectiveness of extracted Gabor texture features, an experimental validation has been conducted on a database of 20 Metal pad images and the experiment has shown no mis-classification.

• 한국CDE학회논문집
• /
• 제3권4호
• /
• pp.223-235
• /
• 1998

A dedicated CAM(Computer-Aided Manufacturing) system has been developed, which generated tool-path to machine Styrofoam stamping die-patterns in Chrysler Corporation. A previous process to build die-patterns was to "stick build" the pattern, in which stock is cut & glued together, and then the NC machining of part-surface shape completes building a Styrofoam die-pattern. The current process utilizes the developed CAM system, and almost removes the manual work, consequently reduces the overall lead time. The paper presents the overall system structures, tool-path generation, and some features of Styrofoam pattern machining.

• 한국의류학회지
• /
• 제40권1호
• /
• pp.171-187
• /
• 2016

The study performed a comparison analysis of market brand patterns for slim-fit dress shirts and analyzed the body surface development figure of men in their 40s using 3D body scan data and developed slim-fit dress shirt patterns suitable for middle-aged men. The sizes of slim-fit dress shirt patterns showed a slight difference depending on brand. The overlap map of slim-fit dress shirt patterns for brands demonstrates how difference of one-dimensional sizes reflect on two-dimensional patterns. This map provides useful information for pattern design and allows and easy recognition of pattern size differences. A try-on system evaluation through 3D-Simulation allows a grasp of the fitness of neckline and size tolerance of under the arms in front, the silhouette of side lines, and overall fitness in front that also allows analysis of the front/back balance of a shirt in side, the size tolerance proportion in front/back, and the fitness of the arm-hole line. Thus, we obtained try-on results that were equivalent to wearing actual clothing. According to the drafting size suggested in the developed final pattern, the total width was 'C/2+5.5cm', and the front was set at 1cm bigger in the size difference of the front and back. The width of the front neck and the back neck was set identically at 'C/12', while the width of the front neck was set to 'C/12+1.5cm'. For the armhole depth, we added 'C/4+2cm', and '0.5cm and 1.5cm' for the width of the front and back to anthropometry. The results of the try-on evaluation through 3D-Simulation indicated that the fitness of the final slim-fit dress shirt pattern was superior to available slim-fit dress shirt patterns on the market and evaluated as superior to the types for middle-aged men.

• 대한원격탐사학회지
• /
• 제24권2호
• /
• pp.117-124
• /
• 2008

지형지물은 각각의 특징적 요인을 내포하고 있다. 이 특징적 요인들은, 공간해상도에 따라 정도의 차이가 있겠지만, 수집된 위성영상에도 반영된다. 이러한 요인들 중에서는 영상분류에 활용될 경우 영상 분류의 정확도를 높혀주고, 때로는 이것이 거의 물체인식의 수준까지 기여할 수 있는 것들이 있다. 이 연구에서는 텍스춰 및 지형지물의 배열에 있어서 특징적 현상을 보이는 비닐하우스를 대상으로 spatial auto-corelation 개념을 기반으로 자동적으로 이를 인지하는 방법을 개발하였다. 사용된 알고리즘은 디지타이징과 같은 사람의 직접적인 개입이 없이 자동화된 방법으로 비닐하우스의 특정한 패턴이 반복적으로 나타나는 것을 감지할 수 있도록 개발되었다. 패틴의 인식에 더하여 비닐하우스의 기하학적 모양을 고려하는 방법도 도입하였다. 그럼으로써 비닐하우스의 추출에 단순히 화소 단위의 분석이 아닌 보다 객체지향적인 방법으로 비닐하우스를 추출하도록 하였다. 개발된 방법을 제주지역의 IKONOS에 적용시켜 본 결과 연구대상지역내의 비닐하우스가 매우 정확하게 적출되었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.1989-2011
• /
• 2019

Vehicle detection based on aerial images is an interesting and challenging research topic. Most of the traditional vehicle detection methods are based on the sliding window search algorithm, but these methods are not sufficient for the extraction of object features, and accompanied with heavy computational costs. Recent studies have shown that convolutional neural network algorithm has made a significant progress in computer vision, especially Faster R-CNN. However, this algorithm mainly detects objects in natural scenes, it is not suitable for detecting small object in aerial view. In this paper, an accurate and effective vehicle detection algorithm based on Faster R-CNN is proposed. Our method fuse a hyperactive feature map network with Eltwise model and Concat model, which is more conducive to the extraction of small object features. Moreover, setting suitable anchor boxes based on the size of the object is used in our model, which also effectively improves the performance of the detection. We evaluate the detection performance of our method on the Munich dataset and our collected dataset, with improvements in accuracy and effectivity compared with other methods. Our model achieves 82.2% in recall rate and 90.2% accuracy rate on Munich dataset, which has increased by 2.5 and 1.3 percentage points respectively over the state-of-the-art methods.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제3권8호
• /
• pp.321-328
• /
• 2014

본 논문에서는 모바일 기기 사용자들의 다음 방문 장소를 효율적으로 예측할 수 있는 맵리듀스 기반의 이동 패턴 마이닝 시스템을 소개한다. 이 시스템은 대용량의 사용자 이동 궤적 데이터 집합으로부터 은닉 마코프 모델로 표현되는 각 사용자의 이동 패턴을 학습해내고, 이 모델을 현재 이동 궤적에 적용함으로써 다음 방문 장소를 예측한다. 본 시스템은 사용자별 이동 패턴 모델을 학습하는 후단부와 실시간으로 다음 방문 장소를 예측하는 전단부 등 크게 두 부분으로 구성된다. 이 중에서 후단부는 주요 장소 추출, 이동 궤적 변환, 이동 패턴 모델 학습 등 총 3개의 맵리듀스 작업 모듈들로 구성된다. 이에 반해, 본 시스템의 전단부는 이동 경로 후보군 생성, 다음 장소 예측 등 총 2개의 작업 모듈들로 구성된다. 그리고 본 시스템을 구성하는 각 작업 모듈의 맵과 리듀스 함수들은 하둡 인프라를 효과적으로 활용하여 병렬 처리를 극대화할 수 있도록 설계하였다. 대용량의 공개 벤치마크 데이터 집합인 GeoLife를 이용하여 본 논문에서 소개한 시스템의 성능을 분석하기 위한 실험들을 수행하였고, 실험 결과를 통해 본 시스템의 높은 성능을 확인할 수 있었다.

• 한국지능시스템학회논문지
• /
• 제16권5호
• /
• pp.556-561
• /
• 2006

DNA칩 영상의 패턴 분류는 인간의 유전적 질병에 대한 유용한 정보를 획득할 수 있다는 점에서 아주 중요한 것이다. 본 논문에서는 DNA칩 영상의 패턴을 분류하기 위해 신경망의 학습 알고리즘 중 Back-propagation과 Self Organizing Map을 이용하여 패턴을 분류하는 알고리즘을 개발하고 이들의 결과를 비교 분석하였다. 또한 개발한 알고리즘은 PC 환경 및 S3C2440 (ARM920T)을 CPU Core로 사용한 MV2440 보드에서 실험하여 그 결과를 디스플레이 함으로써 사용자가 다양한 환경에서 보다 쉽게 유전자 정보를 얻는데 도움을 줄 수 있도록 하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.860-863
• /
• 1997

FCM(Fuzzy Cognitive Map) is a fuzzy signed directed graph for representing causal reasoning which has fuzziness between causal concepts. Authors have already proposed FCM-based fault diagnostic scheme. However, the previously proposed scheme has the problem of lower diagnostic resolution. In order to improve the diagnostic resolution, a new diagnostic scheme based on extended FCM which incorporates the concept of fuzzy number into FCM is developed in this paper. Furthermore, an enhanced TAM(Temporal Associative Memory) recall procedure and pattern matching scheme are also proposed.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.92.3-92
• /
• 2002

A lot of localization algorithms have been developed in order to achieve autonomous navigation. However, most of localization algorithms are restricted to certain conditions. In this paper, Monte Carlo localization scheme with a map-matching algorithm is suggested as a robust localization method for the Public Service Robot to accomplish its tasks autonomously. Monte Carlo localization can be applied to local, global and kidnapping localization problems. A range image based measure function and a geometric pattern matching measure function are applied for map matching algorithm. This map matching method can be applied to both polygonal environments and un-polygonal environments and achieves...

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.42.6-42
• /
• 2002

Kohonen's self organizing feature map (SOFM) converts arbitrary dimensional patterns into one or two dimensional arrays of nodes. Among the many competitive learning algorithms, SOFM proposed by Kohonen is considered to be powerful in the sense that it not only clusters the input pattern adaptively but also organize the output node topologically. SOFM is usually used for a preprocessor or cluster. It can perform dimensional reduction of input patterns and obtain a topology-preserving map that preserves neighborhood relations of the input patterns. The traditional SOFM algorithm[1] is a competitive learning neural network that maps inputs to discrete points that are called nodes on a lattice...