• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.38 no.1
• /
• pp.45-52
• /
• 2001

The proximal isovelocity surface area (PISA) method is an effective way of measuring the regurgitant blood flow rate in the mitral valve. This method defines the modelling required to describe the geometry of the isotach of the PISA. In the normal PISA flow model, the flow rate is calculated assuming that the surface of the isotach is either hemispherical or non-hemispherical numerically. However, this paper evaluated the estimate flow rate using a direct surface subdivision flow model based on the height field after isotach extraction using a region-based scheme. To validate the proposed method, the various PISA flow models were compared using pusatile color Doppler images with flow rates ranging from $30\;cm^3/sec\;to\;60\;cm^3/sec$ flow rate. Whereas the hemispherical flow model had a mean value of $29\;cm^3/sec$ and underestimated the measured flow rate by 35%, the proposed model and non-hemispherical model produced a c;ame mean value of $45\;cm^3/sec$, moreover, both flow models produced a similar pulsatile flow rate.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.1-8
• /
• 2005

In this paper, we propose a two-stage head tracking algorithm adequate for real-time active camera system having pan-tilt-zoom functions. In the color convergence stage, we first assume that the shape of a head is an ellipse and its model color histogram is acquired in advance. Then, the min-shift method is applied to roughly estimate a target position by examining the histogram similarity of the model and a candidate ellipse. To reflect the temporal change of object color and enhance the reliability of mean-shift based tracking, the target histogram obtained in the previous frame is considered to update the model histogram. In the updating process, to alleviate error-accumulation due to outliers in the target ellipse of the previous frame, the target histogram in the previous frame is obtained within an ellipse adaptively shrunken on the basis of the model histogram. In addition, to enhance tracking reliability further, we set the initial position closer to the true position by compensating the global motion, which is rapidly estimated on the basis of two 1-D projection datasets. In the subsequent stage, we refine the position and size of the ellipse obtained in the first stage by using shape information. Here, we define a robust shape-similarity function based on the gradient direction. Extensive experimental results proved that the proposed algorithm performs head hacking well, even when a person moves fast, the head size changes drastically, or the background has many clusters and distracting colors. Also, the propose algorithm can perform tracking with the processing speed of about 30 fps on a standard PC.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.6
• /
• pp.201-211
• /
• 2013

In this paper, we propose a hand tracking and gesture recognition system. Our system employs a depth capture device to obtain 3D geometric information of user's bare hand. In particular, we build a flexible tracking volume and restrict the hand tracking area, so that we can avoid diverse problems caused by conventional object detection/tracking systems. The proposed system computes running average of the hand position, and tracking volume is actively adjusted according to the statistical information that is computed on the basis of uncertainty of the user's hand motion in the 3D space. Once the position of user's hand is obtained, then the system attempts to detect stretched fingers to recognize finger gesture of the user's hand. In order to test the proposed framework, we built a NUI system using the proposed technique, and verified that our system presents very stable performance even in the case that multiple objects exist simultaneously in the crowded environment, as well as in the situation that the scene is occluded temporarily. We also verified that our system ensures running speed of 24-30 frames per second throughout the experiments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.11C
• /
• pp.1071-1076
• /
• 2006

In this paper, we develop face and hand tracking for sign language recognition system. The system is divided into two stages; the initial and tracking stages. In initial stage, we use the skin feature to localize face and hands of signer. The ellipse model on CbCr space is constructed and used to detect skin color. After the skin regions have been segmented, face and hand blobs are defined by using size and facial feature with the assumption that the movement of face is less than that of hands in this signing scenario. In tracking stage, the motion estimation is applied only hand blobs, in which first and second derivative are used to compute the position of prediction of hands. We observed that there are errors in the value of tracking position between two consecutive frames in which velocity has changed abruptly. To improve the tracking performance, our proposed algorithm compensates the error of tracking position by using adaptive search area to re-compute the hand blobs. The experimental results indicate that our proposed method is able to decrease the prediction error up to 96.87% with negligible increase in computational complexity of up to 4%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.2A
• /
• pp.105-112
• /
• 2012

Face detection at a distance faces is very challenging since images are often degraded by blurring and noise as well as low resolution. This paper proposes an improved face detection method with AdaBoost filtering and sequential testing stages with color and shape information. The conventional AdaBoost filter detects face regions but often generates false alarms. The face detection method is improved by adopting sequential testing stages in order to remove false alarms. The testing stages comprise skin-color test and variable edge-mask filtering. The skin-color filtering is composed of two steps, which involve rectangular window regions and individual pixels to generate binary face clusters. The size of the variable edge-mask is determined by the ellipse which is estimated from the face cluster. The validation of the horizontal and vertical ratio of the mask is also investigated. In the experiments, the efficacy of the proposed algorithm is proved by images captured by a CCTV and a smart-phone

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.41-41
• /
• 2017

본 연구는 초분광 영상을 이용하여 수박 모종의 수분함량을 비파괴적으로 추정하기 위해 수행되었다. 단계적으로 수분 스트레스를 받은 수박(n=45) 모종을 초분광 영상시스템으로 촬영하여 모종 영역의 반사율을 추출하였고, 매 촬영 후 모종의 생체중과 건물중을 측정하여 수분함량을 계산하였다. 모종의 반사율과 계측된 수분함량을 변수로 하여 Partial Least Square Regression(PLSR) 분석을 이용하여 수분 추정 모델을 구축하였다. 수분 추정모델을 작성한 결과 Calibration(Cal.)의 정확도($R^2$)는 0.66, 정밀도(RMSE 및 RE)는 각각 1.06%, 1.14%로 나타났다. 수박 모종의 수분함량 추정모델의 정밀도는 상당히 높게 나타났으나 정확도는 낮게 나타났다. 정확도를 개선하기 위해 Confidence ellipses의 신뢰구간을 95%로 설정하였을 때 3개의 모종이 타원 밖에 위치하는 것을 발견하였으며 이를 제거 후 재분석을 하였다. 3개의 모종을 제외한 수박 모종의 수분함량 추정모델의 정확도는 0.82, 정밀도는 0.73%, 0.78%로 나타났다. 3개의 모종을 제외함으로서 모델의 정확도 및 정밀도가 상승하여 3개의 모종이 정확도 및 정밀도를 낮추는 원인이라 판단된다. 작물은 가뭄스트레스를 받을수록 반사율이 낮아지지만(Yang et al., 2010) 3개의 모종은 다른 모종의 수분함량에 비해 반사율이 큰 차이를 나타내어 정확도 및 정밀도를 낮춘 것으로 판단된다. 본 연구를 통해 초분광 영상을 이용하여 수박 모종의 수분함량 추정가능성을 시사하였고, 모델의 정확도를 개선하기 위해 샘플 수 및 수분함량의 변이를 증가시키는 것이 필요하다고 판단된다.

• Journal of Korea Multimedia Society
• /
• v.4 no.2
• /
• pp.116-129
• /
• 2001

To improve the performance of the inverse halftoning, smoothing masks should be designed optimally by using the accurate information of halftone cells. In this thesis, the method of energy minimization is so defined as to determine the exact information of halftone cell. A heuristic search method is proposed to obtain efficiently the parameters of halftone cells which determine the minimum energy. A halftone-peak modeling method with several functions is proposed and used to get initial values of the parameters. The dimension decomposition technique is also adopted to speed up the search process of energy minimization. Several experiments show that the proposed method extracts correct location of the seed pixel of the halftone cell and the extracted information of the halftone cell can be used to get more exactly smoothed color images. The proposed method can be applied to extract the texture patterns, to separate channel images of a scanned color halftone image, and to extract the moire area in an image.