http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
李基聖,韓宗熙 弘益大學校 科學技術硏究所 2003 科學技術硏究論文集 Vol.14 No.-
Multiple mobile robot system is used in industrial, commercial and scientific application areas. Several applications using multiple mobile robots have been reported and supporting theories are still in its early stages because such systems have several problems such as coordination and autonomous navigation in the dynamic environments. In the paper, a hierarchical structure for the cooperative control of multiple mobile robots is proposed. A hierarchical structure has a simple structure and less computing requirement when compared with neural networks and genetic algorithms. The order-level algorithm perceives environments, selects an object to be moved using an object discrimination and determines the robot actions. The action-level algorithm generates a trajectory of each wheel. The simulation results show the effectiveness of the proposed algorithm.
李基聖,韓宗 熙 弘益大學校 科學技術硏究所 2004 科學技術硏究論文集 Vol.15 No.-
A speaker recognition system using a robust matching process is studied. The feature histogram of LPC cepstral coefficients for matching is used. The matching process uses mixture network with penalty scores. Using probability and shape comparison of two feature histograms, similarity values are obtained. The experiment results will be shown to show the effectiveness of the proposed algorithm.
李基聖,李翰九 弘益大學校 科學技術硏究所 2002 科學技術硏究論文集 Vol.13 No.-
The research using a stereo vision system is in progress with an explosion of interest. The main topic of stereo vision system is a recognition of an object in 3D spaces using two or more cameras. In this paper a new method of measuring depth, position and velocity of a moving object is presented. The new algorithm is proposed to reduce the processing time and enable the recognition of object positions in 3 dimensional spaces. In this method, the image system captures moving objects only. Then captured images are used to extract the moving image and find feature points. These points are used in stereo matching. In the proposed algorithm it is needed less time for finding a feature point because the feature point is represented by only one pixel. The results can be used in real time measurement system. The experiment results are shown to show the effectiveness of the proposed algorithm.