• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권5호
• /
• pp.1711-1725
• /
• 2014

Multi-target tracking is the main purpose of many video surveillance applications. Recently, multi-target tracking based on the particle filter method has achieved robust results by using the data association process. However, this method requires many calculations and it is inadequate for real time applications, because the number of associations exponentially increases with the number of measurements and targets. In this paper, to reduce the computational cost of the data association process, we propose a novel multi-target tracking method that excludes particle samples in the overlapped predictive region between the target to track and marginal targets. Moreover, to resolve the occlusion problem, we define an occlusion mode with the normal dynamic mode. When the targets are occluded, the mode is switched to the occlusion mode and the samples are propagated by Gaussian noise without the sampling process of the particle filter. Experimental results demonstrate the robustness of the proposed multi-target tracking method even in occlusion.

• International Journal of CAD/CAM
• /
• 제2권1호
• /
• pp.1-12
• /
• 2002

Computer-Aided Reliable and Optimal Design (CAROD) system is an efficient tool defining the best compromise between cost and safety. Using the concurrent engineering concept, it can supply the designer with all numerical information in the design process. This system integrates several fields such as multidisciplinary optimization, reliability analysis, finite element analysis, geometrical modeling, sensitivity analysis and concurrent engineering. When integrating these disciplines, many difficulties are found such as model coupling and computational time. In this paper, we propose a new concurrent methodology satisfying the reliability requirement, allowing the coupling of different models and reducing the computational time. Two applications (rotating disk and hook structures) demonstrate that CAROD system can be a practical concurrent engineering application for designers.

• 대한전자공학회논문지SP
• /
• 제42권6호
• /
• pp.111-120
• /
• 2005

본 논문에서는 실시간 색역 사상을 위한 3차원 룩업 테이블을 좀더 효과적으로 구현하기 위한 하드웨어 구조를 제시하였다. 기존의 해상도 절감 3차원 룩업 테이블에 대해서 기술하고 하드웨어의 구조를 간소화시킨 해상도 절감 3차원 차분 룩업 테이블의 개념을 소개한다. 새로 제안하는 3차원 차분 룩업 테이블의 경우 기존의 방법과 같이 3차원 룩업 테이블을 8개의 1차원 룩업 테이블로 분해하여 구성하며 색역 사상 규칙은 현재 입력 영상 값과 색역 사상된 출력 값과의 차분 값만을 저장시키고 삼차원 보간 이후에 최종적으로 덧셈기를 추가함으로써 구성한다. 이를 통하여 필요로 하는 하드웨어의 양을 더욱 감축시킬 수 있으며 기존의 방법에 비해서 좀 더 고속으로 구현이 가능하다. 새로 제안된 하드웨어 구조는 FPGA나 ASIC으로 쉽게 구성이 가능하며 실시간 화질 개선의 용도로 쉽게 적용이 가능하다.

• Journal of Multimedia Information System
• /
• 제8권3호
• /
• pp.159-166
• /
• 2021

COVID-19 has dramatically changed people's daily life. Wearing masks is considered as a simple but effective way to defend the spread of the epidemic. Hence, a real-time and accurate mask wearing detection system is important. In this paper, a deep learning-based mask wearing detection system is developed to help people defend against the terrible epidemic. The system consists of three important functions, which are image detection, video detection and real-time detection. To keep a high detection rate, a deep learning-based method is adopted to detect masks. Unfortunately, according to the suddenness of the epidemic, the mask wearing dataset is scarce, so a mask wearing dataset is collected in this paper. Besides, to reduce the computational cost and runtime, a simple online and real-time tracking method is adopted to achieve video detection and monitoring. Furthermore, a function is implemented to call the camera to real-time achieve mask wearing detection. The sufficient results have shown that the developed system can perform well in the mask wearing detection task. The precision, recall, mAP and F1 can achieve 86.6%, 96.7%, 96.2% and 91.4%, respectively.

• 한국CDE학회논문집
• /
• 제22권2호
• /
• pp.215-221
• /
• 2017

This paper describes a method of precise estimation for printing time and material consumption which are directly related to the 3D printing cost. Printing process and head motion of 3D printers using digital printing head, which is analyzed by its digitized steps, is rapidly simulated without slicing to calculate estimated printing results. Using this method, printing time and material usage of 3D printer were estimated quickly and precisely and compared to the real printing result. Applying compensation using the printing parameters, transferred from the 3D printer to the printing estimation system, even more accurate estimation is achieved. This method is used in the 3D Sprint software.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.66-69
• /
• 2003

This paper considers a reinforcement learning(RL) which deals with real environments. Most reinforcement learning studies have been made by simulations because real-environment learning requires large computational cost and much time. Furthermore, it is more difficult to acquire many rewards efficiently in real environments than in virtual ones. The most important requirement to make real-environment learning successful is the appropriate construction of the state space. In this paper, to begin with, I show the basic overview of the reinforcement learning under real environments. Next, 1 introduce a state-space construction method under real environmental which is State Partition Method. Finally I apply this method to a robot navigation problem and compare it with conventional methods.

• 한국전산구조공학회논문집
• /
• 제18권4호통권70호
• /
• pp.445-452
• /
• 2005

본 논문에서는 강박스 거더의 생애주기비용을 최소화하기 위한 방법을 제시하였다. 본 논문에서 고려된 강박스 거더의 생애주기비용은 초기비용, 유지관리비용 및 보수비용으로 구성되었다. 강재 주형의 상태등급곡선과 안전진단 결과 측정된 내하력을 바탕으로 내하력곡선을 추정하였으며, 이 곡선을 이용하여 생애주비용을 고려한 강박스 거더의 최적설계를 수행하였다. 또한 내하력곡선을 통해 강박스 거더의 공용수명과 보수 보강 시기 및 횟수를 결정하고 초기 내하력에 따른 생애주기 동안 발생하는 연간비용을 비교, 분석하였다. 본 논문에서 제안한 생애주기비용을 고려한 강박스 거더의 최적설계를 통하여 기존의 설계에 비해 보다 경제적이며 안전한 설계를 유도할 수 있으리라 판단된다.

• 한국CDE학회논문집
• /
• 제9권2호
• /
• pp.148-157
• /
• 2004

Interactive simulators that simulate mechanical systems are being developed for the purpose of performance evaluation of product design, replacement of physical training, and entertainment game. Use of flight simulator is increasing to reduce risk and cost of physical training, and we need virtual environment which covers large area terrain. We need a method that can reduce development cost and construction time of virtual environment that simulate the real environment. There have been attempts to link GIS or remote sensing field with virtual reality. This paper examines a method that helps to construct virtual environment, and attempts to link geographic information with virtual reality. A construction method of virtual environment based on digital map and satellite image has been studied.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2008년도 학술대회 1부
• /
• pp.78-84
• /
• 2008

이 논문에서는 부채꼴 모양을 가진 요소의 집합으로 3 차원 도자기 모델을 구성하고 사용자가 촉감을 느끼면서 가상공간의 도자기를 제작할 수 있도록 하는 새로운 모델을 제안한다. 변형체를 다루기 위해 기존에 사용하던 유한 요소법(finite element method)과 같은 방법은 모델이 복잡하고 연산량이 많아 실시간 햅틱 렌더링(haptic rendering)에 사용하기에는 많은 제약이 있다. 제안한 모델에서는 도자기 모양의 특징에 착안하여 부채꼴 모양을 가진 요소들이 원통 형태로 모여 쌓여있는 구조를 이용하였다. 이를 통해 요소의 개수를 줄이고 복잡한 연산을 최대한 단순화면서 효율적인 모델링이 가능하도록 하였다.

• 한국CDE학회논문집
• /
• 제10권1호
• /
• pp.11-16
• /
• 2005

CAD/CAM system may have such advantages of cost reduction, production time shortening, and product quality improvement. But current advanced versions of CAD/CAM system for 3-D NC data generation are too much expensive to purchase and too difficult to make full use for small-scale manufacturers whose main products are of 2-D simple shapes. The objective of this paper is to introduce a cost-effective way to 2-D NC data generation with a widely spread CAD software. Using VISUAL LISP in the well-known AUTO-CAD, the contents and steps of an automatic NC data generation program are presented for 2-D machining of contours and pockets. To approve the usefulness of program, a test application to a real part is exhibited also.