• 한국해안·해양공학회논문집
• /
• 제34권1호
• /
• pp.11-18
• /
• 2022

본 연구는 대한해협 인근 입자추적 예측 기법의 정확도 개선을 위해서 해수유동 수치모델 결과를 이용하여 만든 입자추적 모델과 현장 관측 자료를 이용한 기계학습 기반 입자 추적 모델을 비교 및 분석하였다. 세부 연구 방법으로는 대한해협에서 관측된 표층 뜰개 이동 궤적 자료, 3개 관측소(가거도, 거제도, 교본초 관측소)의 조위 및 바람자료를 학습시켜 만든 기계 학습(선형 회귀, 의사결정나무) 기반 예측자료, 수치모델 예측자료(ROMS, MOHID)를 3가지 오차평가방법(CC, RMSE, NCLS)을 통해 비교하였다. 최종 결과로서 CC와 RMSE에서는 의사결정나무 모델의 예측 정확도가 가장 우수하였고 NCLS에서는 MOHID 모델의 예측 결과가 가장 우수하였다.

• 한국가시화정보학회:학술대회논문집
• /
• 한국가시화정보학회 2004년도 Proceedings of 2004 Korea-Japan Joint Seminar on Particle Image Velocimetry
• /
• pp.91-110
• /
• 2004

A comprehensive three-dimensional nano-particle tracking technique in micro- and nano-scale spatial resolution using the Total Internal Reflection Fluorescence Microscope (TIRFM) is discussed. Evanescent waves from the total internal reflection of a 488nm argon-ion laser are used to measure the hindered Brownian diffusion within few hundred nanometers of a glass-water interface. 200-nm fluorescence-coated polystyrene spheres are used as tracers to achieve three-dimensional tracking within the near-wall penetration depth. A novel ratiometric imaging technique coupled with a neural network model is used to tag and track the tracer particles. This technique allows for the determination of the relative depth wise locations of the particles. This analysis, to our knowledge is the first such three-dimensional ratiometric nano-particle tracking velocimetry technique to be applied for measuring Brownian diffusion close to the wall.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권2호
• /
• pp.693-709
• /
• 2018

In this paper, we propose a compact Convolutional Neural Network (CNN)-based tracker in conjunction with a particle filter architecture, in which the CNN model operates as an accurate candidates estimator, while the particle filter predicts the target motion dynamics, lowering the overall number of calculations and refines the resulting target bounding box. Experiments were conducted on the Online Object Tracking Benchmark (OTB) [34] dataset and comparison analysis in respect to other state-of-art has been performed based on accuracy and precision, indicating that the proposed algorithm outperforms all state-of-the-art trackers included in the OTB dataset, specifically, TLD [16], MIL [1], SCM [36] and ASLA [15]. Also, a comprehensive speed performance analysis showed average frames per second (FPS) among the top-10 trackers from the OTB dataset [34].

• 한국항공우주학회지
• /
• 제40권1호
• /
• pp.35-42
• /
• 2012

본 논문은 영상기반항법에서 특징점의 이동변위가 큰 경우에도 추적 성능을 확보할 수 있는 파티클 필터 기반의 특징점 추적 필터를 설계하였다. 기존 KLT(Kanade-Lucas-Tomasi) 알고리즘에서 이동량이 큰 경우의 추적 성능을 향상시키기 위해 특징점의 동역학 모델을 적용하였고, 불규칙적인 영상정보의 특성을 반영하기 위해 파티클 필터를 사용하였다. 저장된 이미지로 KLT 알고리즘과의 특징점 추적 성능을 비교한 결과 제안한 알고리즘은 큰 이동량을 갖는 경우에도 추적 기능을 유지하는 것을 확인하였다.

• 한국수산과학회지
• /
• 제55권6호
• /
• pp.954-959
• /
• 2022

Marine outfalls are used to discharge treated liquid effluents to the environment. An efficiently designed, constructed and operated marine outfall effectively dilutes the discharged effluent, thereby reducing the risk to biota and humans dependent upon the marine environment. In this study, we investigated the effluent transport from a marine outfall at different depths in Masan Bay. A particle-tracking model was used to predict the dispersion of effluent. The model results indicate that some particles released from a depth of 13 m move to the inner area of Masan Bay within 48 h. As the release depth increases after 48 h, the particles move further southward. This suggests that effluent from the outer area of Masan Bay can affect the inner area, and that this effect can be reduced by increasing the depth of effluent release.

• 한국해안·해양공학회논문집
• /
• 제32권4호
• /
• pp.211-222
• /
• 2020

입자추적 실험 결과를 이용하여 새만금 배수갑문 유출수의 영향 범위 파악을 위한 방법론을 수립하고, 2017년을 대상으로 새만금 배수갑문 유출수의 영향 범위를 계절별 확률 분포로 제시하였다. 물질 수송 시간의 지표 중 하나인 water age를 계산하고 입자추적 실험 결과와 비교하여 계산 결과의 타당성을 입증하였다. 배수갑문 유출수는 신시 또는 가력 배수갑문을 중심으로 그 영향 범위가 방사형으로 증가하는데 계절풍의 영향으로 동계에는 남측으로, 하계에는 북측으로 영향 범위가 치우치는 것으로 예측되었다. 예측 결과는 2017년 상황에 한정되지만, 본 연구에서 수립한 입자추적 실험을 이용한 배수갑문 유출수 영향 범위 산정 기법은 현재 변화하고 있는 새만금 해역의 장래 배수갑문 유출수의 영향 범위 산정 연구에 활용이 가능하다.

• 전자공학회논문지
• /
• 제51권9호
• /
• pp.139-147
• /
• 2014

본 논문에서는 다중객체 검출과 동시에 추적을 수행하는 이중계층구조의 파티클 샘플링을 제안한다. 제안된 방법은 다중 객체 검출을 위한 상위 계층 파티클 샘플링과 검출된 객체의 추적을 위한 하위 계층 파티클 샘플링으로 구성된다. 상위 계층에서는 빠른 객체 검출을 위해 슬라이딩 윈도우 대신 움직임 추정 기반의 부모 파티클 (parent particles; PP) 윈도우를 사용하여, 이동 객체 주위로 리샘플링된 파티클을 통해 객체를 검출한다. 하위 계층에서는 상위 계층에서 검출한 객체의 객체영역에 자식 파티클 (child particles; CP)을 생성하여 해당 객체를 추적한다. 실험결과를 통해 비디오 시스템에서 기존 객체 검출 방법보다 빠른 검출이 가능하고, 다중 객체를 효과적으로 추적할 수 있음을 확인하였다.

• ALGAE
• /
• 제34권4호
• /
• pp.315-326
• /
• 2019

Northeastward drifts of massive Sargassum patches were observed in the East China Sea (ECS) and Yellow Sea (YS) by the Geostationary Ocean Color Imager (GOCI) in May 2017. Coverage of the brown macroalgae patches was the largest ever recorded in the ECS and YS. Three-dimensional circulation modeling and Lagrangian particle tracking simulations were conducted to reproduce drifting trajectories of the macroalgae patches. The trajectories of the macroalgae patches were controlled by winds as well as surface currents. A windage (leeway) factor of 1% was chosen based on sensitivity simulations. Southerly winds in May 2017 contributed to farther northward intrusion of the brown macroalgae into the YS. Although satellite observation and numerical modeling have their own limitations and associated uncertainties, the two methods can be combined to find the best estimate of Sargassum patch trajectories. When satellites were unable to capture all patches because of clouds and sea fog in the ECS and YS, the Lagrangian particle tracking model helped to track and restore the missing patches in satellite images. This study suggests that satellite monitoring and numerical modeling are complementary to ensure accurate tracking of macroalgae patches in the ECS and YS.

• ETRI Journal
• /
• 제42권1호
• /
• pp.54-66
• /
• 2020

Nowadays, the broad availability of cameras and embedded systems makes the application of computer vision very promising as a supporting technology for intelligent transportation systems, particularly in the field of vehicle tracking. Although there are several existing trackers, the limitation of using low-cost cameras, besides the relatively low processing power in embedded systems, makes most of these trackers useless. For the tracker to work under those conditions, the video frame rate must be reduced to decrease the burden on computation. However, doing this will make the vehicle seem to move faster on the observer's side. This phenomenon is called the fast motion challenge. This paper proposes a tracker called dynamic swarm particle (DSP), which solves the challenge. The term particle refers to the particle filter, while the term swarm refers to particle swarm optimization (PSO). The fundamental concept of our method is to exploit the continuity of vehicle dynamic motions by creating dynamic models based on PSO. Based on the experiments, DSP achieves a precision of 0.896 and success rate of 0.755. These results are better than those obtained by several other benchmark trackers.

• International Journal of Contents
• /
• 제10권3호
• /
• pp.17-25
• /
• 2014

In this paper, we describe an adaptive Markov chain Monte Carlo-based particle filter that effectively addresses real-time multi-face tracking on mobile platforms. Because traditional approaches based on a particle filter require an enormous number of particles, the processing time is high. This is a serious issue, especially on low performance devices such as mobile phones. To resolve this problem, we developed a tracker that includes a more sophisticated likelihood model to reduce the number of particles and maintain the identity of the tracked faces. In our proposed tracker, the number of particles is adjusted during the sampling process using an adaptive sampling scheme. The adaptive sampling scheme is designed based on the average acceptance ratio of sampled particles of each face. Moreover, a likelihood model based on color information is combined with corner features to improve the accuracy of the sample measurement. The proposed tracker applied on various videos confirmed a significant decrease in processing time compared to traditional approaches.