• Title/Summary/Keyword: similar trajectory

Search Result 166, Processing Time 0.036 seconds

A Fast and Efficient Sliding Window based URV Decomposition Algorithm for Template Tracking (템플릿 추적 문제를 위한 효율적인 슬라이딩 윈도우 기반 URV Decomposition 알고리즘)

  • Lee, Geunseop
    • Journal of Korea Multimedia Society
    • /
    • v.22 no.1
    • /
    • pp.35-43
    • /
    • 2019
  • Template tracking refers to the procedure of finding the most similar image patch corresponding to the given template through an image sequence. In order to obtain more accurate trajectory of the template, the template requires to be updated to reflect various appearance changes as it traverses through an image sequence. To do that, appearance images are used to model appearance variations and these are obtained by the computation of the principal components of the augmented image matrix at every iteration. Unfortunately, it is prohibitively expensive to compute the principal components at every iteration. Thus in this paper, we suggest a new Sliding Window based truncated URV Decomposition (TURVD) algorithm which enables updating their structure by recycling their previous decomposition instead of decomposing the image matrix from the beginning. Specifically, we show an efficient algorithm for updating and downdating the TURVD simultaneously, followed by the rank-one update to the TURVD while tracking the decomposition error accurately and adjusting the truncation level adaptively. Experiments show that the proposed algorithm produces no-meaningful differences but much faster execution speed compared to the typical algorithms in template tracking applications, thereby maintaining a good approximation for the principal components.

Measuring gameplay similarity between human and reinforcement learning artificial intelligence (사람과 강화학습 인공지능의 게임플레이 유사도 측정)

  • Heo, Min-Gu;Park, Chang-Hoon
    • Journal of Korea Game Society
    • /
    • v.20 no.6
    • /
    • pp.63-74
    • /
    • 2020
  • Recently, research on automating game tests using artificial intelligence agents instead of humans is attracting attention. This paper aims to collect play data from human and artificial intelligence and analyze their similarity as a preliminary study for game balancing automation. At this time, constraints were added at the learning stage in order to create artificial intelligence that can play similar to humans. Play datas obtained 14 people and 60 artificial intelligence by playing Flippy bird games 10 times each. The collected datas compared and analyzed for movement trajectory, action position, and dead position using the cosine similarity method. As a result of the analysis, an artificial intelligence agent with a similarity of 0.9 or more with humans was found.

Linkbudget Analysis of Palau Tracking Station Using Antenna Gain of Launch Vehicle (발사체 안테나 이득패턴을 이용한 팔라우추적소 링크버짓 분석)

  • Kim, Chun-Won;Kwon, Soon-Ho;Lee, Tae-Jin;Kim, Dong-Hyun
    • Journal of the Korean Society for Aeronautical & Space Sciences
    • /
    • v.50 no.8
    • /
    • pp.591-597
    • /
    • 2022
  • In this paper, we analyzed linkbudget with comparing actual received level of telemetry system at Palau Tracking Station. Because Palau Tracking Station participated in the launch mission for the first time and lack of verification tests for antenna tracking and signal reception performance, we analyzed the linkbudget more accurately by predicting transmit antenna polarization gain according to the trajectory and attitude of launch vehicle. The analysis results were used to analyze signal reception range, antenna operation angle and LHCP/RHCP received level. The actual received level of the antenna was similar to the linkbudget result as a result of the launch mission operation.

Three-dimensional human activity recognition by forming a movement polygon using posture skeletal data from depth sensor

  • Vishwakarma, Dinesh Kumar;Jain, Konark
    • ETRI Journal
    • /
    • v.44 no.2
    • /
    • pp.286-299
    • /
    • 2022
  • Human activity recognition in real time is a challenging task. Recently, a plethora of studies has been proposed using deep learning architectures. The implementation of these architectures requires the high computing power of the machine and a massive database. However, handcrafted features-based machine learning models need less computing power and very accurate where features are effectively extracted. In this study, we propose a handcrafted model based on three-dimensional sequential skeleton data. The human body skeleton movement over a frame is computed through joint positions in a frame. The joints of these skeletal frames are projected into two-dimensional space, forming a "movement polygon." These polygons are further transformed into a one-dimensional space by computing amplitudes at different angles from the centroid of polygons. The feature vector is formed by the sampling of these amplitudes at different angles. The performance of the algorithm is evaluated using a support vector machine on four public datasets: MSR Action3D, Berkeley MHAD, TST Fall Detection, and NTU-RGB+D, and the highest accuracies achieved on these datasets are 94.13%, 93.34%, 95.7%, and 86.8%, respectively. These accuracies are compared with similar state-of-the-art and show superior performance.

On the wave propagations of football game ball after contacting with the player foot

  • Lei Sun;Cancan Wei;Fei Liu;Lijun Wang;Bo Ren
    • Geomechanics and Engineering
    • /
    • v.33 no.6
    • /
    • pp.529-542
    • /
    • 2023
  • Wave propagation with high transverse deflection could affect the stability of the ball in its trajectory. For low stiffness balls similar to soccer and volleyball balls, the waves are more noticeable in comparison to other balls like ping-pong ball. On the other hand, the soccer balls are under heavy impact loads from shoots and contacting different objects in the field. The maximum recorded speed of a soccer ball after kicking is the 211 km/hr and the average maximum speed is around 112 km/hr. Therefore, in such speeds the aerodynamic forces become important which are directly related to geometrical shape of the ball. In this regard, the wave propagation in soccer ball is examined in the current study using large deformation shear deformable formulations. Classical relations of stress-strain components are taken into consideration along with minimum total energy principle. The final derived relations were solved by using harmonic differential quadrature method. The results are generally presented ion term of phase velocity as function of different influencing parameters of the materials, geometry and mass of the ball.

A New Methodology for the Assessment of Liquefaction Potential Based on the Dynamic Characteristics of Soils (II) : Verification (지반의 동적특성에 기초한 액상화 평가법 (II) : 타당성 검토)

  • 최재순;홍우석;박인준;김수일
    • Journal of the Korean Geotechnical Society
    • /
    • v.18 no.1
    • /
    • pp.101-112
    • /
    • 2002
  • In this study, a new methodology fur the assessment of liquefaction potential is proposed and characteristics of the proposed methodology are verified. The experimental parameter of this methodology, that is, the plastic shear strain trajectory, is compared with the dissipated energy. It is shown that this parameter can express the liquefaction behavior which is generated by excess pore water pressure. This methodology takes advantage of the shear strain time history determined from the site response analysis based on the real time history of earthquake. In this site response analysis, shock type and vibration type records of similar predominant frequency are inputted. The liquefaction safely factors based on the proposed methodology and Korean detailed assessment related to the classical method are calculated from the results of the site response analysis and laboratory dynamic tests. Through this study, it is found that the proposed methodology can not only simulate the liquefaction behavior of saturated soils hut also express the seismic characteristics reasonably : leading type, predominant frequency, maximum acceleration, duration time.

Concentration Variation of Atmospheric Radon and Gaseous Pollutants Related to the Airflow Transport Pathways during 2010~2015 (대기 라돈 및 기체상 오염물질의 기류 이동경로별 농도변화: 2010~2015년 측정)

  • Song, Jung-Min;Kim, Ki-Ju;Bu, Jun-Oh;Kim, Won-Hyung;Kang, Chang-Hee;Chambers, S.
    • Journal of Korean Society for Atmospheric Environment
    • /
    • v.34 no.2
    • /
    • pp.321-330
    • /
    • 2018
  • Concentrations of the atmospheric radon and gaseous pollutants were measured at the Gosan site on Jeju Island from 2010 to 2015, in order to observe their time-series variation characteristics and examine the concentration change related to the airflow transport pathways. Based on the realtime monitoring of the atmospheric radon and gaseous pollutants, the daily mean concentrations of radon ($^{222}Rn$) and gaseous pollutants($SO_2$, CO, $O_3$, $NO_x$) were $2,400mBq\;m^{-3}$ and 1.3, 377.6, 41.1, 3.9 ppb, respectively. On monthly variations of radon, the mean concentration in October was the highest as $3,033mBq\;m^{-3}$, almost twice as that in July ($1,452mBq\;m^{-3}$). The diurnal variation of radon concentration shows bimodal curves at early morning (around 7 a.m.) and near midnight, whereas its lowest concentration was recorded at around 3 p.m. Several gaseous pollutants($SO_2$, CO, $NO_x$) showed a similar seasonal variation with radon concentration as high in winter and low in summer, whereas the $O_3$ concentrations had a bit different seasonal trend. According to the cluster back trajectory analysis, the frequencies of airflow pathways moving from continental North China, East China, Japan and the East Sea, the Korean Peninsula, and North Pacific Ocean routes were 36, 37, 10, 13, and 4%, respectively. When the airflow were moved to Jeju Island from continental China, the concentrations of radon and gaseous pollutants were relatively high. On the other hand, when the airflows were moved from North Pacific Ocean and East Sea, their concentrations were much lower than those from continental China.

Numerical Study on Characteristics of Gas Leakage in an Underground Combined Cycle Power Plant (지하 복합발전 플랜트 내부의 가스 누출 특성에 대한 수치해석 연구)

  • Bang, Joo Won;Sung, Kun Hyuk;Ryou, Hong Sun;Lee, Seong Hyuk
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.17 no.5
    • /
    • pp.594-600
    • /
    • 2016
  • The present study numerically investigated the gas leakage characteristics in a simplified underground combined cycle power plant. The effect of obstacles near a crack location on the gas concentration in the confined space was analyzed by using the lower flammable limit (LFL) of methane gas. When the jet flow was close to the vertical walls, the longitudinal leakage distance increased by about 60% (when an obstacles was present) compared to the case without any obstacle, because these obstacles prevented transverse flows. In addition, when an air filter was installed near to the trajectory of the gas flow, the longitudinal leakage distance was similar to the distance between the crack and obstacle, whereas the transverse leakage distance increased up to 8 times compared to the case without any obstacle. As the jet flow impacts on the obstacle and changes its direction, the gas flows recirculate. Therefore, it is necessary to consider the effect of the structure and facility locations on the trajectory of the jet flow to propose an accident prevention system in confined spaces.

The Effect of 2008 Beijing Olympic on Korean Air Quality (2008년 북경 올림픽이 한반도 대기질에 미치는 영향)

  • Song, Hyung-Do;Choi, Jin-Soo;Hong, Sung-Chel;Chang, lim-Seok;Kim, Jung-Soo;Lee, Suk-Jo
    • Journal of Environmental Science International
    • /
    • v.18 no.6
    • /
    • pp.655-665
    • /
    • 2009
  • This study aims to identify the impacts of air quality in the Korean Peninsula according to the China's environmental policies in preparation of the Beijing 2008 Olympic Games. The measurement of emission variations in China, aircraft measurement, and modelling were carried out. The reduction measures in Beijing, China and its emission changes resulted in $30{\sim}65%$ in decrease out of the total emissions within the Beijing region, whereas when it comes to the whole nation of China, the reduction rate was about $4{\sim}9%$. Comparing the concentration of the air pollutants in Seoul and Ganghwa in August 2008 during around the period of Beijing Olympic Games with one in $2004{\sim}2007$ showed that the $SO_2$ concentrations in the past was above 5ppb, while the concentration in the 2008 olympic period was 4ppb and below. The NOx at the Seokmori site in Ganghwa tended to be lower in concentration in 2008 than in between $2004{\sim}2007$. As for $O_3$ and $PM_{2.5}$, the concentration tended to be rather low since August 11. The air current track that showed during the period of aircraft measurement presented to be flowed into Korea through the Northeast part of China and the coast of Bohai Bay, while the concentrations of $SO_2$. NOx, and $O_3$ over the west sea on August 20 and 24 were 0.54 (0.28ppb), 0.86 (1.84ppb), and 54.0 (41.5ppb) respectively, similar or lower than the ones measured in the past in the similar current patterns. The modelling result showed similar patterns to the data of aircraft measurement, in particular in $SO_2$. Overall, the reduction measures in Beijing, China affected directly and indirectly the air quality in the Korean peninsular, but the impact was not significant as it was momentary and limited to the intended area.

Size Distribution Characteristics of Water-soluble Ionic Components in Airborne Particulate Matter in Busan (부산 도심지역 대기중 입자상물질의 크기분포에 따른 수용성 이온성분의 특성)

  • Park, Gee-hyeong;Lee, Byeong-kyu
    • Journal of Korean Society for Atmospheric Environment
    • /
    • v.31 no.3
    • /
    • pp.287-301
    • /
    • 2015
  • This study was conducted to investigate size distribution characteristics of water-soluble ionic components in the airborne particulate matter (PM) collected from an urban area in Busan using a MOUDI cascade impactor from March to October 2010. The inorganic constituents in the fine particles (${\leq}1.8{\mu}m$) predominantly consisted of sulfate, nitrate, ammonium, and potassium. Sulfate and ammonium concentrations showed a high correlation and similar equivalent concentrations in the fine modes including $0.18{\sim}0.32{\mu}m$, $0.32{\sim}0.56{\mu}m$, and $0.56{\sim}1.0{\mu}m$. This indicates that the main chemical component in the fine particles would be forms of ammonium sulfate such as $(NH_4)_3H(SO_4)_2$, $(NH_4)_2SO_4$, and $(NH_4)HSO_4$. Back trajectory analysis showed that relatively higher concentrations of ammonium, nitrate, and sulfate in the fine mode, compared to the coarse mode, are caused both by domestic sources and long-range transports originated from China continent. High concentration episodes of PM both in the fine mode and the coarse mode were attributed both by anthropogenic sources, such as ship emissions and traffic emissions, and by natural sources such as seawater (sea salt), respectively.