• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.9-12
• /
• 2019

지난 수 년 동안 계속해서 일반 실상 카메라를 이용한 영상분석기술에 대한 연구가 활발히 진행되고 있다. 최근에는 딥러닝 기술을 적용한 지능형 영상분석기술로 발전해 왔으며 국방기지방호, CCTV, 사용자 얼굴인식, 머신비전, 자동차, 드론 산업이 활성화되면서 많은 시너지를 효과를 일으키고 있다. 그러나 어두운 밤과 안개, 날씨, 연기 등 다양한 여건에서 따라서 카메라의 영상분석 정확성 감소와 오류가 수반될 수 있으며 일반적으로 딥러닝 기술을 활용하기 위해서는 고사양의 GPU를 필요로 하기 때문에 다른 추가적인 시스템이 요구된다. 이에 본 연구에서는 열적외선 영상의 객체 검출에 적용하기 위해 SSD(Single Shot MultiBox Detector) 기반의 경량적인 MobilNet 네트워크로 재구성하여, 모바일 기기 등 낮은 사양의 낮은 임베디드 시스템에서도 활용 할 수 있는 방법을 제안한다. 모의 실험결과 제안된 방식의 모델은 적외선 열화상 카메라에서 객체검출과 학습시간이 줄어든 것을 확인 할 수 있었다.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.260-270
• /
• 2023

We introduce a novel Visual Inertial Odometry (VIO) algorithm designed to improve the performance of thermal-inertial odometry. Thermal infrared image, though advantageous for feature extraction in low-light conditions, typically suffers from a high noise level and significant information loss during the 8-bit conversion. Our algorithm overcomes these limitations by approximating a 14-bit raw pixel histogram into a Gaussian mixture model. The conversion method effectively emphasizes image regions where texture for visual tracking is abundant while reduces unnecessary background information. We incorporate the robust learning-based feature extraction and matching methods, SuperPoint and SuperGlue, and zero velocity detection module to further reduce the uncertainty of visual odometry. Tested across various datasets, the proposed algorithm shows improved performance compared to other state-of-the-art VIO algorithms, paving the way for robust thermal-inertial odometry.

• Proceedings of the KIPE Conference
• /
• 2020.08a
• /
• pp.209-211
• /
• 2020

운송기관의 온실가스 저감을 위해 배터리-수소연료전지 하이브리드 철도추진시스템에 대한 연구가 활발히 진행되고 있다. 이 중 배터리는 빠른 응답 특성으로 하이브리드 철도추진 시스템의 효율을 극대화 시키기 위해 주요 전원으로 사용되고 있어, 시스템의 안전성 및 신뢰성을 높이기 위해 정확한 열화추정이 요구되고 있다. 본 논문에서는 사전 모델의 수립이 필요하지 않고 미소 용량 및 폐회로 제어가 가능한 재귀 최소제곱 추정 기법을 이용한 리튬이온 배터리의 SOH 추정 기법을 제안하였으며, 1S18P 배터리 모듈을 통해 열화 추정결과를 검증하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.740-742
• /
• 2023

객체 인식 연구에 있어서 딥러닝 기반의 사람 인식에 있어서 많은 연구들이 공개되고 있다. 특히 화재사고에 있어서 연기로 인해 가시성이 떨어져 인명구조에 어려움이 발생한다. 이에 열화상 카메라와 딥러닝을 통해 사람을 인식하는 기술이 연구되고 있다. 기존 연구에서는 열화상 카메라와 YOLO 딥러닝을 통해 사람을 인식하는데 95%의 성능을 보였지만, YOLO는 그리드 셀에서 하나의 분류만하기 때문에 물체에 가려진 사람을 판별하는데 정확도가 낮았다. 본 논문에서는 이와 같은 한계를 극복하기 위해 기존 Faster R-CNN 알고리즘을 사용한다. 신체부위 Guided Attention mechanism을 사용하여 가중치를 준 Feature Map을 RPN에 적용시켜 학습모델을 구현한다면 더 높은 정확도를 얻을 수 있다. 향후 본 논문에서 제안하는 기법은 많은 실험과 다양한 데이터 셋을 통해 실질적인 검증을 할 예정이다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.14 no.4
• /
• pp.293-306
• /
• 1989

In this paper, the models and characteristics of multipath propagation in an urban environment are described. Three propagation models(a random model, a ray model and a method of estimating time delay is proposed based on the envelope correlation between two radio frequencies. It is shown on the basis of laboratory simulation and field tests that the simple two-ray model is an adequate model for the fundamental study of the multipath propagation characteristic of the mobile radiowave and the estimating time delays of multipath-propagated waves in an urban area.

• 전자공학회논문지 IE
• /
• v.44 no.2
• /
• pp.1-7
• /
• 2007

The increasing high frequency capabilities of CMOS have resulted in increased RF and analog design in CMOS. Design of RF and analog circuits depends critically on device S-parameter characteristics, magnitude of real and imaginary components and their behavior as a function of frequency. Utilization of scaled high performance CMOS technologies poses challenges as concerns for reliability degradation mechanisms increase. It is important to understand and quantify the effects of the reliability degradation mechanisms on the S-parameters and in turn on small signal model parameters. Various physical effects influencing small-signal parameters, especially the transconductance and capacitances and their degradation dependence, are discussed in detail. The measured S-parameters of H-gate and T-gate devices in a frequency range from 0.5GHz to 40GHz. All intrinsic and extrinsic parameters are extracted from S-parameters measurements at a single bias point in saturation. In this paper we discuss the analysis of the small signal equivalent circuits of RF SOI MOSFET's verificated for the purpose of exacting the change of parameter of small signal equivalent model followed by device flame.

• Journal of the Korea Concrete Institute
• /
• v.15 no.1
• /
• pp.25-34
• /
• 2003

The degradation of reinforced concrete (RC) structures due to physical and chemical attacks has been a major issue in construction engineering. Deterioration of RC structures by chloride attack followed by reinforcement corrosion is one of the serious problems. An objective of this study is to develop a form of mathematical model of chloride ingress into concrete. In order to overcome some limits of the previous approaches, a chloride ingress model, consisting of chloride solution intrusion through the capillary pore and chloride ion diffusion through the pore water, was proposed. Moreover, the variability of chloride ion diffusivity due to the degree of hydration of cement, relative humidity in pore, exposure condition, and variation of chloride binding, was considered in the model. In order to verify the proposed model, the results predicted by the proposed model were compared with analysis results of Life-365, a computer program for predicting the service life of reinforced concrete structures exposed to chlorides. In conclusion, the proposed model would be promising to predict the chloride ion profile and to estimate the service life of RC structures.

• Journal of the Korea Concrete Institute
• /
• v.20 no.1
• /
• pp.13-22
• /
• 2008

The initiation and growth processes of cyclic ice body in porous systems are affected by the thermo-physical and mass transport properties, as well as gradients of temperature and chemical potentials. Furthermore, the diffusivity of deicing chemicals shows significantly higher value under cyclic freeze-thaw conditions. Consequently, the disintegration of concrete structures is aggravated at marine environments, higher altitudes, and northern areas. However, the properties of cyclic freeze-thaw with crack growth and the deterioration by the accumulated damages are hard to identify in tests. In order to predict the accumulated damages by cyclic freeze-thaw, a regression analysis by the response surface method (RSM) is used. The important parameters for cyclic freeze-thawdeterioration of concrete structures, such as water to cement ratio, entrained air pores, and the number of cycles of freezing and thawing, are used to compose the limit state function. The regression equation fitted to the important deterioration criteria, such as accumulated plastic deformation, relative dynamic modulus, or equivalent plastic deformations, were used as the probabilistic evaluations of performance for the degraded structural resistance. The predicted results of relative dynamic modulus and residual strains after 300 cycles of freeze-thaw show very good agreements with the experimental results. The RSM result can be used to predict the probability of occurrence for designer specified critical values. Therefore, it is possible to evaluate the life cycle management of concrete structures considering the accumulated damages due to the cyclic freeze-thaw using the proposed prediction method.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.11 no.2
• /
• pp.131-140
• /
• 2009

It has been repeatedly reported that a drainage system of a drained tunnel is deteriorated. And consequently the water pressure on the lining increases with time. However, little research on the watertight tunnel was found in the literatures. According to field measurements, leakage of the undrained tunnel has increased with time, which is completely opposite to the behavior of the drained tunnel. It is evident that the hydraulic deterioration of the tunnel lining changes the water pressure on the lining and the amount of leakage, thus the design coneept in terms of groundwater is not maintained tightly throughout the life time of the tunnel. The Segment lining is generally constructed as watertight. However, it is frequently reported that the leakage in the segment tunnel increases with time. It is also reported that the leakage is generally concentrated at the joints of the segments. In this study structural and hydraulic interaetion of the segment lining due to the hydraulic deterioration of the segments and the joints is investigated using the numerical modeling method. An electric utility tunnel below groundwater table is considered for the analyses. The effects of hydraulic deterioration of the segment lining are identified in terms of ground loading, water pressure and lining behavior. A remedial grouting measure for leakage is also numerically simulated, and its appropriateness is evaluated.

• Magazine of the Korea Concrete Institute
• /
• v.9 no.5
• /
• pp.157-164
• /
• 1997

일반적으로 콘크리트와 철근간의 경계면을 나타내는 유한요소법에는 균열의 부근에서 발생하는 부착열화 현상을 고려하지 않고 있다. 이것은 균열 부근에서 과도한 부착을 초래하고 , 국소 변형과 균열의 진전에도 영향을 준다. 본 연구에서는 철근콘크리트 구조물의 균열부근에서 일어나는 부착거동의 변화를 고려한 비선형 부착응력-미끄럼 모델을 제안하였다. 철근과 콘크리트간의 경계면에는 링크요소를 이용하였고, 링크의 특성은 철근을 가로지르는 균열의 상태에 따라 변하도록 조정하였다. 균열의 형성상태를 정량화하고, 부착거동을 두 포락선 1) 균열로부터 충분히 떨어진 위치에서의 부착상태를 모델링한 외연포락선, 2)횡균열면에 있어서의 부착상태를 모델링한 내연포락선의 사이에 변이시키기 위하여 비국소적 손상도 개념을 도입하였다. 이 방법의 유효성을 알아보기 위하여 편재하중을 받는 T형 교각의 실험 및 해석결과를 제시하였다. 제안된 모델의 결과를 실험결과와 비교하여 본 모델의 유용성을 검증하였다.