http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Parallel optimal control with multiple shooting, constraintsaggregation and adjoint methods
Moongu Jeon 한국전산응용수학회 2005 Journal of applied mathematics & informatics Vol.19 No.1-2
In this paper, constraint aggregation is combined with the adjoint and multiple shooting strategies for optimal control of differential algebraic equations (DAE) systems. The approach retains the inherent parallelism of the conventional multiple shooting method, while also being much more efficient for large scale problems. Constraint aggregation is employed to reduce the number of nonlinear continuity constraints in each multiple shooting interval, and its derivatives are computed by the adjoint DAE solver DASPKADJOINT together with ADIFOR and TAMC, the automatic differentiation software for forward and reverse mode, respectively. Numerical experiments demonstrate the effectiveness of the approach.
전태균 ( Taegyun Jeon ),전문구 ( Moongu Jeon ) 한국정보처리학회 2012 한국정보처리학회 학술대회논문집 Vol.19 No.2
본 연구에서는 일반 야외 영상 및 항공 시뮬레이션 영상에 대한 지형 분석을 위해 영역 기반장면 분할 기법을 제시한다. 영역의 분류를 위해 MeanShift 기법을 기반으로 한 표현과 Texton, SIFT, 위치정보를 특징으로 하는 기법을 제안하고 실험을 통해 주요 대상 영역이 분할되는 결과를 보인다. Sowerby 데이터 셋과 Google Earth 데이터로부터 자체적으로 제작한 데이터 셋에 대해 실험하였으며 수풀지형, 초목지형, 도로 등에 대해 분류하였다.
Seokhyoung Lee,Moongu Jeon,Shin, V. IEEE 2012 IEEE transactions on industrial electronics Vol.59 No.11
<P>A new distributed fusion filtering algorithm for linear multiple time-delayed systems is proposed. The multisensory distributed fusion filter is formed by the summation of local Kalman filters having time delays (LKFTDs) in both the system and measurement models. The proposed distributed filter has a parallel structure that enables processing of multisensory measurements; thereby, it is more reliable than the centralized version if some sensors turn faulty. The key contribution of this paper is the derivation of recursive error cross-covariance equations between the LKFTDs to compute the optimal matrix fusion weights. In the particular case of multisensory dynamic systems having time delays in only the measurement model, the obtained results coincide with the previous work of Sun. The high accuracy and efficiency of the proposed distributed filter are then demonstrated through its implementation on a vehicle suspension system.</P>
Vehicle Detection Using Local Size-Specific Classifiers
NOH, SeungJong,JEON, Moongu 'Institute of Electronics, Information and Communi 2016 IEICE transactions on information and systems Vol.99e.d No.9
<P>As the number of surveillance cameras keeps increasing, the demand for automated traffic-monitoring systems is growing. In this paper, we propose a practical vehicle detection method for such systems. In the last decade, vehicle detection mainly has been performed by employing an image scan strategy based on sliding windows whereby a pre-trained appearance model is applied to all image areas. In this approach, because the appearance models are built from vehicle sample images, the normalization of the scales and aspect ratios of samples can significantly influence the performance of vehicle detection. Thus, to successfully apply sliding window schemes to detection, it is crucial to select the normalization sizes very carefully in a wise manner. To address this, we present a novel vehicle detection technique. In contrast to conventional methods that determine the normalization sizes without considering given scene conditions, our technique first learns local region-specific size models based on scene-contextual clues, and then utilizes the obtained size models to normalize samples to construct more elaborate appearance models, namely local size-specific classifiers ( LSCs). LSCs can provide advantages in terms of both accuracy and operational speed because they ignore unnecessary information on vehicles that are observable in faraway areas from each sliding window position. We conduct experiments on real highway traffic videos, and demonstrate that the proposed method achieves a 16% increased detection accuracy with at least 3 times faster operational speed compared with the state-of-the-art technique.</P>
New design of a VirtualGlove for grasping applications
Wang, Hyuk,Jeon, Moongu,Lee, Yong-Gu Wiley Subscription Services, Inc., A Wiley Company 2010 Human factors and ergonomics in manufacturing Vol.20 No.4
<P>Virtual gloves have received much attention in the field of virtual reality and computer simulations. They are considered to be essential tools for implementing any sort of hand-based experiences in virtual environments. For applications with simpler motions, the accuracy of finger-bending amount returned by these virtual gloves is not of primary interest. For grasping applications, however, inaccuracy in the bending amount results in unrealistic scenarios having discrepancies in the contact geometry for the hand and the object. In this study, we improve the measurements of bending amount by placing the bend sensors on the palm of the hand, where the objects are touched directly. Supporting evaluative data and design details are also discussed. © 2010 Wiley Periodicals, Inc.</P>
( Sergey Yun ),( Moongu Jeon ) 한국정보처리학회 2014 한국정보처리학회 학술대회논문집 Vol.21 No.1
In this work we present a robust and fast approach to estimate 3D vehicle pose that can provide results under a specific traffic surveillance conditions. Such limitations are expressed by single fixed CCTV camera that is located relatively high above the ground, its pitch axes is parallel to the reference plane and the camera focus assumed to be known. The benefit of our framework that it does not require prior training, camera calibration and does not heavily rely on 3D model shape as most common technics do. Also it deals with a bad shape condition of the objects as we focused on low resolution surveillance scenes. Pose estimation task is presented as PnP problem to solve it we use well known “POSIT” algorithm [1]. In order to use this algorithm at least 4 non coplanar point’s correspondence is required. To find such we propose a set of techniques based on model and scene geometry. Our framework can be applied in real time video sequence. Results for estimated vehicle pose are shown in real image scene.