Due to the sewer induced ground subsidence, there is an increasing demand for the advanced visual inspection technique for the existing sewer pipe structures. This study aim to develop a new condition assessment method using visual inspection device with automatic crack extracting and real-time gas monitoring systems for large diameter glass-fiber reinforced plastic sewer pipes. In this paper, a high-precision image capturing system that automatically extracts cracks in the large-diameter sewer pipes and sewage culverts with a diameter of 1,000 mm or more, and a real-time gas detection sensor for investigator safety were considered. By analyzing the module technology of the visual inspection device, the test device and their software for system integration were developed. It is expected that the developed technique inspecting conditions of the GFRP sewer pipes using the proposed visual inspection device in this study can be effectively used for various types of underground structures in the future.

This study introduces the web-camera image processing-based natural landmark extraction method for automatic welding using 3-axis stage. The welding is a highly significant process in the industries of shipbuilding, automobile, construction, machinery, and so on. However, it has been avoided due to poor working conditions such as fume, spatter, noise, and so on. For the automatic welding system, the web-camera is used to extract the natural landmarks which can give the relative coordinate to set up the initial position of the stage for the welding process. The Canny edge and Hough transformation have been used to extract the significant points for the natural landmark extraction in this paper.

기존의 “비트매니아”와 같은 리듬게임은 게임 개발자가 해당 음악의 악보에 맞게 노트를 생성하여 사용자가 정확히 연주 할수록 좋은 결과가 나오도록 구현되어 있다. 하지만 선택할 수 있는 노래가 제한되어 있다는 단점이 있다. 따라서 본 논문에서는 사용자가 자신이 원하는 음악을 플레이할 수 있도록 mp3와 같은 디지털 오디오 파일을 FFT 알고리즘을 이용하여 실시간으로 음계를 추출하고 정렬한 뒤 게임 인터페이스 상에 노트를 생성한다. 또한 BPM정보를 이용하여 노트의 생성 순서와 게임의 난이도를 조절한다.

Due to the industrialization and urbanization, the transport of hazardous materials increases, which rises possibilities in occurring prospective accidents in terms of hazardous material transport as well. This study applied the model developed from the previous research to analyze the scale of damage areas from the accidents related to hazardous material accidents, as well as suggested a method to measure automatically the scale of accident including casualties and environmental damage based on the guideline which suggests the quantities of hazardous materials exposed from an accident and was defined in the study of standardization for hazardous material classification. A buffering analysis technique of Geographic Information System (GIS) was applied for that. To apply the model which evaluates the scale of population and exposure to environment on each link, rail network, zones, rail accident data, rail freight trips, and locations of rivers etc were complied as a database for GIS analysis. In conclusion, a method to measure damage areas by the types of hazardous materials was introduced using a Clip and a Special Join technique for overlay analysis.

최근 대량으로 쏟아지는 감성공학 연구 결과와 논문들을 가치 있는 자료로 만들기 위해서는 감성 데이터가 산업 전반에 활용될 수 있도록 지표로 정리해야 한다. 본 논문에서는 "웹기반 감성 데이터 베이스 구축 및 보급에 관한 연구" 과제를 통해 작성된 감성 데이터 지표에 입각해서 앞으로 대량으로 출현할 감성공학 데이터의 지속적인 지표화를 위한 과정의 자동화를 제안한다. 문서 데이터의 지표화 작업이 자동요약과 유사하다는 점에 착안하여 자동지표화 시스템을 위한 기술들의 기초가 되는 정보유형 및 주요어 추출, 특성표현을 통한 정보문 추출에 대해 감성공학 코퍼스 분석을 통해 연구하고자 한다. 이는 감성공학 분야에서의 지식관리 시스템이나 자동요약 시스템에 활용될 수 있다. 활용될 수 있다.

임의의 체눈 모양에서 어떤 절점에서 출발하여 출발한 절점으로 되돌아 오는 최단 경로를 탐색함으로써 2차원 유한요소의 연결관계를 자동추출할 수 있는 방법을 개발하였다. 한 절점에서 가능한 여러 경로 중에서 가능성이 큰 경로만을 탐색하게 하였고 추출된 경로에 대하여 요소로서의 유일성 및 적합성을 검사하였다. 제안된 방법이 완전함을 증명하였으며 예제를 통하여 일반적인 자동발생 기능의 적용이 어려운 체눈 모양에 대해서도 정확하게 요소를 추출할 수 있음을 보였다.

Quantizing and extracting visual features of mushroom(Lentinus edodes L.) are crucial to the sorting and grading automation, the growth state measurement, and the dried performance indexing. A computer image processing system was utilized for the extraction and measurement of visual features of front and back sides of the mushroom. The image processing system is composed of the IBM PC compatible 386DK, ITEX PCVISION Plus frame grabber, B/W CCD camera, VGA color graphic monitor, and image output RGB monitor. In this paper, an automatic thresholding algorithm was developed to yield the segmented binary image representing skin states of the front and back sides. An eight directional Freeman's chain coding was modified to solve the edge disconnectivity by gradually expanding the mask size of 3×3 to 9×9. A real scaled geometric quantity of the object was directly extracted from the 8-directional chain element. The external shape of the mushroom was analyzed and converted to the quantitative feature patterns. Efficient algorithms for the extraction of the selected feature patterns and the recognition of the front and back side were developed. The developed algorithms were coded in a menu driven way using MSC language Ver.6.0, PC VISION PLUS library fuctions, and VGA graphic functions.

This paper presents a procedure for automated extraction of ridge shadows in noisy gray images. This procedure mainly consists of 1) a deformable model which is designed basing upon the knowledge about the shape of shadows and is expected to be useful in extracting ridge shadows especially located in low signal to noise ratio background, and 2) the scale space scheme which is also useful even if there is less information about the size and the positions of ridge shadows in advance. This procedure is applied to artificial images and its performance is evaluated experimentally.