• Journal of Broadcast Engineering
• /
• v.22 no.3
• /
• pp.366-374
• /
• 2017

Since a display device such as TV or digital signage is getting larger, the types of media is getting changed into wider view one such as UHD, panoramic and jigsaw-like media. Especially, panoramic and jigsaw-like media is realized by stitching video clips, which are captured by different camera or devices. However, a stitching process takes long time, and has difficulties in applying for a real-time process. Thus, this paper suggests to find out 2D Adjacency Matrix, which tells spatial relationships among those video clips in order to decrease a stitching processing time. Using the Discrete Cosine Transform (DCT), we convert the each frame of video source from the spatial domain (2D) into frequency domain. Based on the aforementioned features, 2D Adjacency Matrix of images could be found that we can efficiently make the spatial map of the images by using DCT. This paper proposes a new method of generating 2D adjacency matrix by using DCT for producing a panoramic and jigsaw-like media through various individual video clips.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.2
• /
• pp.287-296
• /
• 2011

Thirty six female students participated in the experiment of the fat mass weight loss. they kept diary for foods they ate every day, took a picture of the foods, transmitted the picture to the experimenter by the camera phone, and consulted him about fat mass loss once a week for 8 weeks period. Fat mass weight and its related factors of the students had been measured repeatedly every week during 8 weeks, The repeated measurement data were used for applying various random coefficient models. And hence optimal random coefficient model was selected. From the optimal model, the baseline, body mass index, diastolic blood pressure, total cholesterol and time of the fixed factors were very significant. The fixed quadratic time effect existed. The variance components corresponding to the subject effect, linear time effect of the random coefficients were all positive. Thus random coefficients up to the linear terms were considered as the optimal model. The treatment effect reduced the weight loss to an average of 2.1kg at the end of the period.

• Korean Journal of Applied Biomechanics
• /
• v.14 no.1
• /
• pp.161-172
• /
• 2004

본 연구의 목적은 각기 다른 수직 점프 동작 시 근육의 길이와 근육의 수축속도 변화를 비교 분석하는데 있다. 피험자의 운동학적 변인들을 분석하기 위해 2대의 고감도 카메라를 (60 Hz, Panasonic AG455) 사용하여 점프 동작을 촬영하였다. 대퇴직근, 내측광근, 외측광근, 중간광근, 대퇴이두근(단두), 내측과 외측 비복근의 길이와 근수축 속도는 Brand et al. (1982)에 의해 제시되어진 하지근 기시 정지점의 3차원 좌표값과 동작분석을 통한 하지 분절간의 회전 및 변환행렬을 사용하여 측정되어졌다. 일반적인 근육 길이와 수축속도의 변화 형태는 각기 다른 점프간에 매우 유사한 형태를 보였다. 상승기 초기에 대퇴사두근의 길이가 최대인것으로 나타났으며, 이에 반해 대퇴이두근과 내외측 비복근은 공중 동작이 발생하는 시점에 근의 길이가 최대인 것으로 나타났다. 근육의 길이 변화 범위는 대퇴직근이 35.9에서 47.5 cm, 외측광근이 29.4에서 38.8 cm, 중간광근이 31.5에서 38.0 cm, 내측광근이 30.9에서 38.6 cm, 대퇴이두근이 21.3에서 39.1 cm, 외측비복근이 31.4에서 33.5 cm, 내측비복근이 30.5에서 33.2 cm인 것으로 나타났다. SQ와 CMJ에서는 대퇴사두근의 최대 단축성 수축 속도와 대퇴이두근과 내외측 비복근의 최대 신장성 수축이 공중동작이 발생하기 바로 전에 이루어졌다. 대퇴사두근의 최대 신장성 수축과 대퇴이두근과 내외측 비복근의 최대 단축성 수축은 일반적으로 피험자가 착지하는 순간에 발생되어졌다. 그러나 HJ와 DJ에서는 대퇴사두근의 최대 신장성 추축과 대퇴이두근과 내외측 비복근의 최대 신장성 수축이 하강기 초반에 발생되어졌다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.1
• /
• pp.6-11
• /
• 2011

In this paper, we propose a gait-based human identification system using eigenfeature regularization and extraction (ERE). First, a gait feature for human identification which is called gait energy image (GEI) is generated from walking sequences acquired from a camera sensor. In training phase, regularized transformation matrix is obtained by applying ERE to the gallery GEI dataset, and the gallery GEI dataset is projected onto the eigenspace to obtain galley features. In testing phase, the probe GEI dataset is projected onto the eigenspace created in training phase and determine the identity by using a nearest neighbor classifier. Experiments are carried out on the CASIA gait dataset A to evaluate the performance of the proposed system. Experimental results show that the proposed system is better than previous works in terms of correct classification rate.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.4
• /
• pp.23-35
• /
• 2012

This paper presents a 3-D pose (position and orientation) estimation method for an elliptic object in 3-D space. It is difficult to resolve the problem of determining 3-D pose parameters with respect to an elliptic feature in 3-D space by interpretation of its projected feature onto an image plane. As an alternative, we propose a two points-based pose estimation algorithm to seek the 3-D information of an elliptic feature. The proposed algorithm determines a homogeneous transformation uniquely for a given correspondence set of an ellipse and two coplanar points that are defined on model and image plane, respectively. For each plane, two triangular features are extracted from an ellipse and two points based on the polarity in 2-D projection space. A planar homography is first estimated by the triangular feature correspondences, then decomposed into 3-D pose parameters. The proposed method is evaluated through a series of experiments for analyzing the errors of 3-D pose estimation and the sensitivity with respect to point locations.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.6
• /
• pp.499-506
• /
• 2004

The copper foil surface inspection system is necessary for the factory automation and product quality. The developed system is composed of the high speed line scan camera, the image capture board and the processing computer. For the system resource utilization and real-time processing, multi-threaded architecture is introduced. There are one image capture thread, 2 or more defect detection threads, and one defect communication thread. To process the high-speed input image data, the I/O overlap is used through the double buffering. The defect is first detected by the predetermined threshold. To cope with the light irregularity, the compensation process is applied. After defect detection, defect type is classified with the defect width, eigenvalue ratio of the defect covariance matrix and gray level of defect. In experiment, for high-speed input image data, real-time processing is possible with multi -threaded architecture, and the 89.4% of the total 141 defects correctly classified.

• Journal of Korea Society of Industrial Information Systems
• /
• v.13 no.1
• /
• pp.37-45
• /
• 2008

This paper proposes a half-silvered mirror display system designed to demonstrate useful information about things on display into the air. It helps the spectators gain quick access to information near the area where the things are put on display. This paper deals with three matters: First, tracking based on camera images created in real time enables the provision of information about the things that are both still and moving. Second, as information is output based on the real-time coordinates of things on display, the parallel processing-based tracking algorithm is used to ensure smooth transfer. Third, a half-mirror is placed in front of the display area to establish an augmented reality system and visual distortion caused by mirror angle is adjusted by the reflection transformation matrix. The objectives of this system are to arouse the spectators' interest in things on display and offer easy and quick access to information about them.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.28 no.1
• /
• pp.9-18
• /
• 2015

In this paper, we verify the optimal topology design for heat conduction problems in steady stated which is obtained numerically using the adjoint design sensitivity analysis(DSA) method. In adjoint variable method(AVM), the already factorized system matrix is utilized to obtain the adjoint solution so that its computation cost is trivial for the sensitivity. For the topology optimization, the design variables are parameterized into normalized bulk material densities. The objective function and constraint are the thermal compliance of the structure and the allowable volume, respectively. For the experimental validation of the optimal topology design, we compare the results with those that have identical volume but designed intuitively using a thermal imaging camera. To manufacture the optimal design, we apply a simple numerical method to convert it into point cloud data and perform CAD modeling using commercial reverse engineering software. Based on the CAD model, we manufacture the optimal topology design by CNC.

• Journal of KIISE:Software and Applications
• /
• v.36 no.6
• /
• pp.471-478
• /
• 2009

Recently, researches for user interface are remarkably processed due to the explosive growth of 3-dimensional contents and applications, and the spread class of computer user. This paper proposes a novel method to manipulate windows efficiently using only the intuitive motion of hand. Previous methods have some drawbacks such as burden of expensive device, high complexity of gesture recognition, assistance of additional information using marker, and so on. To improve the defects, we propose a novel visual touchless interface. First, we detect hand region using hue channel in HSV color space to control window using hand. The distance transform method is applied to detect centroid of hand and curvature of hand contour is used to determine position of fingertips. Finally, by using the hand motion information, we recognize hand gesture as one of predefined seven motions. Recognized hand gesture is to be a command to control window. In the proposed method, user can manipulate windows with sense of depth in the real environment because the method adopts stereo camera. Intuitive manipulation is also available because the proposed method supports visual touch for the virtual object, which user want to manipulate, only using simple motions of hand. Finally, the efficiency of the proposed method is verified via an application based on our proposed interface.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.200-207
• /
• 2020

Recently, deep neural networks such as CNN are showing excellent performance in various fields such as image classification, object recognition, visual quality enhancement, etc. However, as the model size and computational complexity of deep learning models for most applications increases, it is hard to apply neural networks to IoT and mobile environments. Therefore, neural network compression algorithms for reducing the model size while keeping the performance have been being studied. In this paper, we apply few compression methods to CNN models and evaluate their performances in the embedded environment. For evaluate the performance, the classification performance and inference time of the original CNN models and the compressed CNN models on the image inputted by the camera are evaluated in the embedded board equipped with QCS605, which is a customized AI chip. In this paper, a few CNN models of MobileNetV2, ResNet50, and VGG-16 are compressed by applying the methods of pruning and matrix decomposition. The experimental results show that the compressed models give not only the model size reduction of 1.3~11.2 times at a classification performance loss of less than 2% compared to the original model, but also the inference time reduction of 1.2~2.21 times, and the memory reduction of 1.2~3.8 times in the embedded board.