• Title/Summary/Keyword: Local Minimum

Search Result 222, Processing Time 0.491 seconds

Analysis of Facial Movement According to Opposite Emotions (상반된 감성에 따른 안면 움직임 차이에 대한 분석)

  • Lee, Eui Chul;Kim, Yoon-Kyoung;Bea, Min-Kyoung;Kim, Han-Sol
    • The Journal of the Korea Contents Association
    • /
    • v.15 no.10
    • /
    • pp.1-9
    • /
    • 2015
  • In this paper, a study on facial movements are analyzed in terms of opposite emotion stimuli by image processing of Kinect facial image. To induce two opposite emotion pairs such as "Sad - Excitement"and "Contentment - Angry" which are oppositely positioned onto Russell's 2D emotion model, both visual and auditory stimuli are given to subjects. Firstly, 31 main points are chosen among 121 facial feature points of active appearance model obtained from Kinect Face Tracking SDK. Then, pixel changes around 31 main points are analyzed. In here, local minimum shift matching method is used in order to solve a problem of non-linear facial movement. At results, right and left side facial movements were occurred in cases of "Sad" and "Excitement" emotions, respectively. Left side facial movement was comparatively more occurred in case of "Contentment" emotion. In contrast, both left and right side movements were occurred in case of "Angry" emotion.

Optimal Design of Municipal Water Distribution System (관수로 시스템의 최적설계)

  • Ahn, Tae Jin;Park, Jung Eung
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.14 no.6
    • /
    • pp.1375-1383
    • /
    • 1994
  • The water distribution system problem consists of finding a minimum cost system design subject to hydraulic and operational constraints. Since the municipal water distribution system problem is nonconvex with multiple local minima, classical optimization methods find a local optimum. An outer flow search - inner optimization procedure is proposed for choosing a better local minimum for the water distribution systems. The pipe network is judiciously subjected to the outer search scheme which chooses alternative flow configurations to find an optimal flow division among pipes. Because the problem is nonconvex, a global search scheme called Stochastic Probing method is employed to permit a local optimum seeking method to migrate among various local minima. A local minimizer is employed for the design of least cost diameters for pipes in the network. The algorithm can also be employed for optimal design of parallel expansion of existing networks. In this paper one municipal water distribution system is considered. The optimal solutions thus found have significantly smaller costs than the ones reported previously by other researchers.

  • PDF

STK Feature Tracking Using BMA for Fast Feature Displacement Convergence (빠른 피쳐변위수렴을 위한 BMA을 이용한 STK 피쳐 추적)

  • Jin, Kyung-Chan;Cho, Jin-Ho
    • Journal of the Korean Institute of Telematics and Electronics S
    • /
    • v.36S no.8
    • /
    • pp.81-87
    • /
    • 1999
  • In general, feature detection and tracking algorithms is classified by EBGM using Garbor-jet, NNC-R and STK algorithm using pixel eigenvalue. In those algorithms, EBGM and NCC-R detect features with feature model, but STK algorithm has a characteristics of an automatic feature selection. In this paper, to solve the initial problem of NR tracking in STK algorithm, we detected features using STK algorithm in modelled feature region and tracked features with NR method. In tracking, to improve the tracking accuracy for features by NR method, we proposed BMA-NR method. We evaluated that BMA-NR method was superior to NBMA-NR in that feature tracking accuracy, since BMA-NR method was able to solve the local minimum problem due to search window size of NR.

  • PDF

Robust Face and Facial Feature Tracking in Image Sequences (연속 영상에서 강인한 얼굴 및 얼굴 특징 추적)

  • Jang, Kyung-Shik;Lee, Chan-Hee
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.14 no.9
    • /
    • pp.1972-1978
    • /
    • 2010
  • AAM(Active Appearance Model) is one of the most effective ways to detect deformable 2D objects and is a kind of mathematical optimization methods. The cost function is a convex function because it is a least-square function, but the search space is not convex space so it is not guaranteed that a local minimum is the optimal solution. That is, if the initial value does not depart from around the global minimum, it converges to a local minimum, so it is difficult to detect face contour correctly. In this study, an AAM-based face tracking algorithm is proposed, which is robust to various lighting conditions and backgrounds. Eye detection is performed using SIFT and Genetic algorithm, the information of eye are used for AAM's initial matching information. Through experiments, it is verified that the proposed AAM-based face tracking method is more robust with respect to pose and background of face than the conventional basic AAM-based face tracking method.

Human Body Motion Tracking Using ICP and Particle Filter (반복 최근접점와 파티클 필터를 이용한 인간 신체 움직임 추적)

  • Kim, Dae-Hwan;Kim, Hyo-Jung;Kim, Dai-Jin
    • Journal of KIISE:Software and Applications
    • /
    • v.36 no.12
    • /
    • pp.977-985
    • /
    • 2009
  • This paper proposes a real-time algorithm for tracking the fast moving human body. Although Iterative closest point (ICP) algorithm is suitable for real-time tracking due to its efficiency and low computational complexity, ICP often fails to converge when the human body moves fast because the closest point may be mistakenly selected and trapped in a local minimum. To overcome such limitation, we combine a particle filter based on a motion history information with the ICP. The proposed human body motion tracking algorithm reduces the search space for each limb by employing a hierarchical tree structure, and enables tracking of the fast moving human bodies by using the motion prediction based on the motion history. Experimental results show that the proposed human body motion tracking provides accurate tracking performance and fast convergence rate.

Characteristics of Sea Breezes at Coastal Area in Boseong (보성 해안 지역에서의 해풍 특성)

  • Lim, Hee-Jeong;Lee, Young-Hee
    • Atmosphere
    • /
    • v.29 no.1
    • /
    • pp.41-51
    • /
    • 2019
  • The characteristics of the sea breeze were investigated using the wind and temperature data collected from 300-m tower at Boseong from May 2014 to April 2018. Sea breeze day was detected using following criteria: 1) the presence of a clear change in wind direction near sunrise (between 1 hour after sunrise and 5 hours before sunset) and sunset (from 1500 LST to midnight), 2) presence of thermal forcing of sea breeze and 3) no heavy precipitation (rain < $10mm\;d^{-1}$). Sea breeze days occurred on 569 days for 4 years. The monthly distribution of sea breeze day occurrence shows maxima in May and September and minimum in December. The average onset and cessation times of the sea breeze are 0942 LST and 1802 LST, respectively. Although the 10-m wind shows clockwise rotation with time in the afternoon, the observed hodograph does not show an ideal elliptical shape and has different characteristics depending on the upper synoptic wind direction. Vertical structure of sea breeze shows local maximum of wind speed and local minimum of virtual potential temperature at 40 m in the afternoon for most synoptic conditions except for southeasterly synoptic wind ($60^{\circ}{\sim}150^{\circ}$) which is in the same direction as onshore flow. The local minimum of temperature is due to cold advection by sea breeze. During daytime, the intensity of inversion layer above 40 m is strongest in westerly synoptic wind ($240^{\circ}{\sim}330^{\circ}$) which is in the opposite direction to onshore flow.

Motion estimation algorithm using motion vectors of neighboring blocks (인접 블록의 움직임 벡터를 이용한 움직임 예측 알고리즘)

  • Jun Younghyun;Yun Jongho;Cho Hwahyun;Choi Myungryul
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2005.11a
    • /
    • pp.742-744
    • /
    • 2005
  • 본 논문에서는 인접 블록의 움직임 벡터를 이용한 움직임 예측 알고리즘을 제안하였다. 제안된 알고리즘은 두개의 탐색 단계로 구성된다. 첫 번째 단계는 인접 블록의 움직임 벡터를 이용한 탐색점에서 오차값이 제일 작은 위치를 초기 시작 위치로 사용하였다. 두 번째 단계는 첫 번째 단계에서 찾은 시작 위치에서 정확한 움직임 예측을 위한 패턴과 방법을 적용 하였다. 제안된 알고리즘은 움직임 벡터가 클 경우에 불필요한 탐색점 개수를 줄이고, 성능저하의 원인인 지역적 최소값(local minimum)에 빠질 위험을 감소시켰다. 제안된 알고리즘은 NTSS, 4SS, IDFS, ARPS와 비교 했으며, 성능면에서는 평균 PSNR이 $0.27\~2.56dB$향상되었고, 탐색점 개수면에서는 평균 27개 감소 하였다.

  • PDF

Stable Model for Active Contour based Region Tracking using Level Set PDE

  • Lee, Suk-Ho
    • Journal of information and communication convergence engineering
    • /
    • v.9 no.6
    • /
    • pp.666-670
    • /
    • 2011
  • In this paper, we propose a stable active contour based tracking method which utilizes the bimodal segmentation technique to obtain a background color diminished image frame. The proposed method overcomes the drawback of the Mansouri model which is liable to fall into a local minimum state when colors appear in the background that are similar to the target colors. The Mansouri model has been a foundation for active contour based tracking methods, since it is derived from a probability based interpretation. By stabilizing the model with the proposed speed function, the proposed model opens the way to extend probability based active contour tracking for practical applications.

A Model-based 3-D Pose Estimation Method from Line Correspondences of Polyhedral Objects

  • Kang, Dong-Joong;Ha, Jong-Eun
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2003.10a
    • /
    • pp.762-766
    • /
    • 2003
  • In this paper, we present a new approach to solve the problem of estimating the camera 3-D location and orientation from a matched set of 3-D model and 2-D image features. An iterative least-square method is used to solve both rotation and translation simultaneously. Because conventional methods that solved for rotation first and then translation do not provide good solutions, we derive an error equation using roll-pitch-yaw angle to present the rotation matrix. To minimize the error equation, Levenberg-Marquardt algorithm is introduced with uniform sampling strategy of rotation space to avoid stuck in local minimum. Experimental results using real images are presented.

  • PDF

A Fast Motion Estimation Algorithm with Motion Analysis (움직임 해석을 통한 고속 움직임 예측 알고리즘)

  • Jun, Young-Hyun;Yun, Jong-Ho;Cho, Hwa-Hyun;Choi, Myung-Ryul
    • Proceedings of the IEEK Conference
    • /
    • 2005.11a
    • /
    • pp.339-342
    • /
    • 2005
  • We present an efficient block-based motion estimation algorithm with motion analysis. The motion analysis determines a size of search pattern and a maximum repeated count of search pattern. In case of large movement in large image, we reduce search points and the local minimum which caused by low performance. The proposed algorithm employs with searching step of 2. The first step determines an initial search point with neighbor block vector and a size of initial search pattern. The second step determines a size of search pattern and a maximum repeated count with motion analysis. We improve motion prediction accuracy while reducing required computational complexity compared to other fast block-based motion estimation algorithms.

  • PDF