• Journal of the Korean Geotechnical Society
• /
• v.21 no.9
• /
• pp.87-102
• /
• 2005

In the congested urban areas, tunnelling close to existing structures or services often occurs due to the lack of surface space so that tunnelling-induced ground movements may cause a serious damage to the adjacent structures. This study focused on the two dimensional laboratory model pile-soil-tunnelling interaction tests using a close range photogrammetric technique. Testing equipments and procedures were Introduced, particularly features of aluminium rods regarded as the frictional granular material. The experimental result showed that the photo imaging process by the VMS and EngVis programs proved to be a useful tool in measuring the pile tip movements during the tunnelling. Consequently, the normalised pile tip movement data for the influence zones can be generated by the laboratory model tests using the Photogrammetric technique. This study presents influence zones associated with the normalized pile tip settlements due to tunnelling in the cohesionless material. The influence zones were Identified by both a laboratory model test and a numerical analysis. The normalized pile tip movements from the model test were in good agreement with the numerical analysis result. The influence zones proposed in this study could be used to decide the reasonable location of tunnel construction in the planning stage. However, the scale of model pile and model tunnel sizes must be carefully adjusted as real ones for practical application considering the ground conditions at a given site.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.145-151
• /
• 2023

3D-CNN is one of the deep learning techniques for learning time series data. Such three-dimensional learning can generate many parameters, so that high-performance machine learning is required or can have a large impact on the learning rate. When learning dynamic hand-gestures in spatiotemporal domain, it is necessary for the improvement of the efficiency of dynamic hand-gesture learning with 3D-CNN to find the optimal conditions of input video data by analyzing the learning accuracy according to the spatiotemporal change of input video data without structural change of the 3D-CNN model. First, the time ratio between dynamic hand-gesture actions is adjusted by setting the learning interval of image frames in the dynamic hand-gesture video data. Second, through 2D cross-correlation analysis between classes, similarity between image frames of input video data is measured and normalized to obtain an average value between frames and analyze learning accuracy. Based on this analysis, this work proposed two methods to effectively select input video data for 3D-CNN deep learning of dynamic hand-gestures. Experimental results showed that the learning interval of image data frames and the similarity of image frames between classes can affect the accuracy of the learning model.

• Cartoon and Animation Studies
• /
• s.29
• /
• pp.103-128
• /
• 2012

Study about existence of illusion which human beings feel from imitated image based reality have been continuing by copy theory and conventionalism for a long time. Traditional copy theory which had controlled representation theory from plato have explained illusion by similarity of image and representation objects. According to copy theory, image is natural sign unlike language but the late in the 20th century, conventionalism from N, Goodman insists they are not any special similarity between image and representation objects. They insist image and conventional sign just as language. These opposit theory rearranged conventionalism by the entrance on the cognitive science. The copy theory couldn't explain the problem of representational gap between reality and duplication, but photo media makes new paradigm about theory of the illusion. The problem of representational gap was disappeared by CGI images on the base of digital media. We are exposed exquisite duplication for a example, movie, advertisement, printings. Sometimes duplications are more real than the original works. Digital is a non-material object by 0 and 1. Specially real lighting skill and mechanism are copied perfectly by photon mapping skills and the duplications are produced more real than the original works. By disappearance of representational gap, we need new theory model for explaining of digital illusion and copy theory can be the key.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.897-902
• /
• 2007

인간과 컴퓨터간의 전통적인 인터페이스는 인간이 요구하는 다양한 인터페이스를 제공하지 못한다는 점에서 점차 사용하기 불편하게 되었고 이는 새로운 형태의 인터페이스에 대한 요구로 이어지게 되었다. 본 논문에서는 이러한 추세에 맞추어 카메라를 통해 인간의 손 제스처를 인식하는 새로운 인터페이스를 연구하였다. 손은 자유도가 높고 3차원의 view direction에 의해 형상이 매우 심하게 변한다. 따라서 윤곽선 기반방법과 같은 2차원으로 투영된 영상에서 contour나 edge의 정보로 손 제스처를 인식하는 데는 한계가 있다. 그러나 모델기반 방법은 3차원 정보를 이용하기 때문에 손 제스처를 인식하는데 좋으나 계산량이 많아 실시간으로 처리하기가 쉽지 않다. 이러한 문제점을 해결하기 위해 손 형상에 대한 대규모 데이터베이스를 구성하고 정규화된 공간에서 Feature 간의 연관성을 파악하여 훈련 데이터 모델을 구성하여 비교함으로써 실시간으로 손 포즈를 구별할 수 있다. 이러한 통계적 학습 기반의 알고리즘은 다양한 데이터와 좋은 feature의 검출이 최적의 성능을 구현하는 것과 연관된다. 따라서 배경으로부터 노이즈를 최대한 줄이기 위해 피부의 색상 정보를 이용하여 손 후보 영역을 검출하고 검출된 후보 영역으로부터 HLF(Haar-like Feature)를 이용하여 손 영역을 검출한다. 검출된 손 영역으로부터 패턴 분류 과정을 거쳐 손 포즈를 인식 하게 된다. 패턴 분류 과정은 HLF를 이용하여 손 포즈를 인식하게 되는데 미리 학습된 각 포즈에 대한 HLF를 이용하여 손 포즈를 인식하게 된다. HLF는 Violar가 얼굴 검출에 적용한 것으로 얼굴 검출에 좋은 결과를 보여 주었으며, 이는 적분 이미지로부터 추출한 HLF를 이용한 Adaboost 학습 알고리즘을 사용하였다. 본 논문에서는 피부색의 색상 정보를 이용 배경과 손 영상을 최대한 분리하여 배경의 대부분이 Adaboost-Haar Classifier의 첫 번째 스테이지에서 제거되는 방법을 이용하여 그 성능을 더 향상 시켜 손 형상 인식에 적용하였다.

• Journal of Digital Convergence
• /
• v.13 no.2
• /
• pp.159-175
• /
• 2015

The two-dimensional QR code has advantages such as directional nature, enough data storage capacity, ability of error correction, and ability of data restoration. There are two major issues like speed and correctiveness of recognition in the two-dimensional QR code. Therefore, this paper proposes a morphology-based algorithm of detecting the interest region of a barcode. Our research contents can be summarized as follows. First, the interest region of a barcode image was detected by close operations in morphology. Second, after that, the boundary of the barcode are detected by intersecting four cross line outside in a code. Three, the projected image is then rectified into a two-dimensional barcode in a square shape by the reverse-perspective transform. In result, it shows that our detection and recognition rates for the barcode image is also 97.20% and 94.80%, respectively and that outperforms than previous methods in various illumination and distorted image environments.

• Geophysics and Geophysical Exploration
• /
• v.14 no.3
• /
• pp.214-219
• /
• 2011

We perform the frequency-domain waveform inversion based on the residual-selection strategy. In the residual-selection strategy, we classify time-domain residual wavefields into several groups according to the order of absolute amplitudes. Because the residual wavefields are normalized after regularization of the gradient directions within each group, the residual-selection strategy plays a role in enhancing the small-amplitude wavefields, which contributes to improving the deep parts of inverted subsurface images. After classifying residuals in the time domain, they are transformed to the frequency domain. Waveform inversion is performed in the frequency domain using the back-propagation technique which has been popularly used in reverse-time migration. The residual-selection strategy is applied to the SEG/EAGE salt and IFP Marmousi models. Numerical results show that the residual-selection strategy yields better results than the conventional frequency-domain waveform inversion.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.8B
• /
• pp.1549-1557
• /
• 1999

In this paper, we propose a face recognition algorithm based on the differential image method-DCT This algorithm uses neural networks which is flexible for noise. Using the same condition (same luminous intensity and same distance from the fixed CCD camera to human face), we have captured two images. One doesn't contain human face. The other contains human face. Differential image method is used to separate the second image into face region and background region. After that, we have extracted square area from the face region, which is based on the edge distribution. This square region is used as the characteristics region of human face. It contains the eye bows, the eyes, the nose, and the mouth. After executing DCT for this square region, we have extracted the feature vectors. The feature vectors were normalized and used as the input vectors of the neural network. Simulation results show 100% recognition rate when face images were learned and 92.25% recognition rate when face images weren't learned for 30 persons.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.5
• /
• pp.969-976
• /
• 2019

A lightweight artificial intelligence hardware has made great strides in many application areas. In general, a lightweight artificial intelligence system consist of lightweight artificial intelligence engine and preprocessor including feature selection, generation, extraction, and normalization. In order to achieve optimal performance in broad range of applications, lightweight artificial intelligence system needs to choose a good preprocessing function and set their respective hyper-parameters. This paper proposes a unified framework for a lightweight artificial intelligence system and utilization method for finding models with optimal performance to use on a given dataset. The proposed unified framework can easily generate a model combined with preprocessing functions and lightweight artificial intelligence engine. In performance evaluation using handwritten image dataset and fall detection dataset measured with inertial sensor, the proposed unified framework showed building optimal artificial intelligence models with over 90% test accuracy.

• Journal of the Korean Geotechnical Society
• /
• v.23 no.9
• /
• pp.29-37
• /
• 2007

The experiments have been conducted on Kaolinite in laboratory to investigate the development of shrinkage cracking and propose a simple model. Image analysis method consisting of control point selection(CPS) technique is used to process and analyze images of soil cracking captured by a digital camera. The distributions of crack length increment and crack area increment vary as a three-step process. These steps are regarded as stages of soil cracking. They are in turn primary crack, secondary crack and shrinkage crack stages. In case of crack area, the primary and secondary stages end at normalized gravimetric water content(NGWC) of 0.92 and 0.70 for different specimen thicknesses respectively. In addition, the primary stage in case of crack length also ends at NGWC of 0.92 while the secondary stage stops at NGWC of 0.79, 0.82, and 0.85 for the sample thicknesses of 0.5, 1.0, and 2.0 cm respectively Based on the experimental results, the distributions of crack length increment and crack area increment appear to be linear with a decrease of NGWC. Therefore, the development of shrinkage cracking is proposed typically by a simple model functioned by a combination of three linear expressions.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.11 no.4
• /
• pp.94-100
• /
• 2008

Recently, global warming for climate system is a crucial issue over the world and it brings about severe climate change, abnormal temperature, a downpour, a drought, and so on. Especially, a drought over the earth surface accelerates desertification which has been advanced over the several years mainly originated from a climatic change. The objective of this study is to detect variation of vegetation water condition around China and Mongolia desert by using satellite data having advantage in observing surface biological system. In this study, we use SPOT/VEGETATION satellite image to calculate NDWI (Normalized Difference Water Index) around study area desert for monitoring of status of vegetation characteristics. The vegetation water status index from remotely sensing data is related to desertification since dry vegetation is apt to desertify. We can infer vegetation water status using NDWI acquired by NIR (Near infrared) and SWIR (Short wave infrared) bands from SPOT/VGT. The consequence is that NDWI decreased around desert from 1999 to 2006. The areas that NDWI was decreased are located in the northeast of Mongolian Gobi desert and the southeast of China Taklamakan desert.