• Journal of KIISE
• /
• v.45 no.2
• /
• pp.157-164
• /
• 2018

Due to the revolutionary advances in deep learning, performance of pattern recognition has increased significantly in many applications like speech recognition and image recognition, and some systems outperform human-level intelligence in specific domains. Unlike pattern recognition, in this paper, we focus on generating Korean sentences based on a few Korean sentences. We apply variational recurrent auto-encoder (VRAE) and modify the model considering some characteristics of Korean sentences. To reduce the number of words in the model, we apply a word spacing model. Also, there are many Korean sentences which have the same meaning but different word order, even without subjects or objects; therefore we change the unidirectional encoder of VRAE into a bidirectional encoder. In addition, we apply an interpolation method on the encoded vectors from the given sentences, so that we can generate new sentences which are similar to the given sentences. In experiments, we confirm that our proposed method generates better sentences which are semantically more similar to the given sentences.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.3
• /
• pp.21-29
• /
• 2011

This paper presents a method that estimates distance and velocity of an object with reliability regardless of maneuver status of the target in stereo vision system. A stereo vision system can calculate a distance with disparity from left and right images. However, the distance estimation error may occur due to quantization error of image pixel. A sub-pixel interpolation method minimizes the quantization error and estimates accurate disparity with real value. Extended Kalman filter (EKF) was used to minimize the error covariance and estimate the object's velocity. However, divergence problem occurs due to model uncertainty when a target maneuvers highly, which makes the estimation error increase. In this paper, we propose a virtual model extended Kalman filter (VMEKF) method that minimizes the processing time and provides reliable estimation ability regardless of maneuver status. Computer simulations and experimental results in real road environments demonstrate that the proposed method gives a reliable estimation performance and reduces processing time under various maneuver status while comparing other estimation filters.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.4 s.316
• /
• pp.109-116
• /
• 2007

Most harmonic synthesis methods using phase information employ a quadratic or cubic phase interpolation. The methods are computationally expensive to implement because every component sinewave must be synthesized on a per sample basis. In this paper, we propose a fast harmonic synthesis method for sinusoidal speech/audio coding based on the quadratic and cubic phase function to overcome the complexity problem. To derive the fast harmonic synthesis method, we define the over-sampling function and phase modulation function by constraining the parameter of phase function to be independent for harmonic index and derive the fast synthesis method using IFFT. Experimental results show that the proposed method significantly reduce the complexity of conventional cosine synthesis method while maintaining the performance.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.42 no.1
• /
• pp.61-68
• /
• 2005

Image-based rendering is an approach to generate realistic images in real-time without modeling explicit 3D geometry. Especially, owing to its simplicity, TIP(Tour Into the Picture) is preferred to constructing a 3D background scene. Because existing TIP methods have a limitation in that they lack geometrical information, we can not expect a accurate scene if the viewpoint is far from the origin of the TIP. In this paper, we propose the method of constructing a virtual environment of a wide area by blending multiple TIP images. Firstly, we construct multiple TIP models of the virtual environment. Then we interpolate foreground and background objects respectively, to generate a smooth navigation image. The method proposed here can be applied to various industry applications, such as computer game, 3D car navigation, and so on.

• Journal of Internet Computing and Services
• /
• v.7 no.4
• /
• pp.45-55
• /
• 2006

This paper proposes a virtual target overlay technique for a realistic training simulation which projects a virtual target on ground-based CCD images according to an appointed scenario. This method creates a realistic 3D model for instructors by using high resolution GeoTIFF (Geographic Tag Image File Format) satellite images and DTED(Digital Terrain Elevation Data), and it extracts road areas from the given CCD images for both instructors and trainees, Since there is much difference in observation position, resolution, and scale between satellite Images and ground-based sensor images, feature-based matching faces difficulty, Hence, we propose a moving synchronization technique that projects the targets on sensor images according to the moving paths marked on 3D satellite images. Experimental results show the effectiveness of the proposed algorithm with satellite and sensor images of Daejoen.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.7
• /
• pp.71-80
• /
• 1999

Sign-language communication can be a useful way of exchanging message between people who using different languages. In this paper, we report an experimental survey on the construction of a Korean-Japanese sign-language communication system using 3D model. For real-time communication, we introduced an intelligent communication method and built the system as a client-server architecture on the Internet. A character model is stored previously in the clients and a series of animation parameters are sent instead of real image data. The input-sentence is converted into a series of parameters of Korean sign language or Japanese sign language at server. The parameters are transmitted to clients and used for generating the animation. We also employ the emotional expressions, variable frames allocation method, and a cubic spline interpolation for the purpose of enhancing the reality of animation. The proposed system is implemented with Visual $C^{++}$ and Open Inventor library on Windows platform. Experimental results show a possibility that the system could be used as a non-verbal communication means beyond the linguistic barrier.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.100-100
• /
• 2019

최근 대기 중 미세먼지의 농도가 높은 일수가 급증하면서, 미세먼지를 저감하고자 하는 연구가 활발히 이루어지고 있다. 미세먼지는 주로 자동차 혹은 공장 등 인간 활동에 의한 오염물질 배출에 의해 발생하는 것으로 알려져 있으며, 태양복사에너지, 토양수분, 강우, 풍속 등의 수문기상학적 인자에 의해 발생, 이동, 소멸의 과정을 거친다. 현재 우리나라에서는 미세먼지 농도를 관측하기 위해 지점 기반의 관측소를 운영하고 있으며, 관측소가 위치하지 않은 지역의 미세먼지 농도는 선형 보간법 등을 활용한 내삽 기법을 통해 제공하고 있다. 그러나 미세먼지 농도는 다양한 수문기상인자들의 영향에 의한 차이가 크게 나타나기 때문에 지점 기반의 자료로는 해당 지역의 미세먼지 농도를 추정하는 데 어려움이 많다. 본 연구에서는 미세먼지의 공간적인 분포를 추정하고자 MODerate resolution Imaging Spectroradiometer (MODIS) 에어로졸 자료와 Global Land Data Assimilation System (GLDAS) 수문기상인자를 활용하여 미세먼지 농도에 영향을 주는 것으로 판단되는 다양한 수문기상인자들과의 상관성을 분석하였다. 미세먼지와 각 인자간의 상관성을 분석하여 높은 상관성을 갖는 수문기상인자들을 도출하고 최적의 선형회귀분석 모델을 구축하기 위해 베이지안 모델 평균(Bayesian Model Averaging, BMA)을 사용하였으며, 지점 데이터와의 비교를 통해 활용성을 검증하였다. 전체적으로 수문기상인자를 사용한 선형회귀분석 결과에서는 미세먼지농도 변화의 경향을 반영하고 있는 것을 확인할 수 있었으나, 계절별, 지역별 등 대기 특성을 고려하지 않아 각 기간의 급격한 농도 변화를 감지하기에 어려움이 있었다. 이러한 연구를 바탕으로 수문기상인자와 미세먼지 농도의 패턴이 더욱 정확히 분석된다면, 미세먼지 농도 모니터링과 정확한 예보 시스템의 구축에 효과적으로 활용 될 것으로 기대된다.

• Journal of the Korean Geotechnical Society
• /
• v.37 no.5
• /
• pp.47-63
• /
• 2021

Recently, the demand for three-dimensional (3D) underground maps from the perspective of digital twins and the demand for linkage utilization are increasing. However, the vastness of national geotechnical survey data and the uncertainty in applying geostatistical techniques pose challenges in modeling underground regional geotechnical characteristics. In this study, an optimal learning model based on multi-layer perceptron (MLP) was constructed for 3D subsurface lithological and geotechnical classification in Seoul, South Korea. First, the geotechnical layer and 3D spatial coordinates of each borehole dataset in the Seoul area were constructed as a geotechnical database according to a standardized format, and data pre-processing such as correction and normalization of missing values for machine learning was performed. An optimal fitting model was designed through hyperparameter optimization of the MLP model and model performance evaluation, such as precision and accuracy tests. Then, a 3D grid network locally assigning geotechnical layer classification was constructed by applying an MLP-based bet-fitting model for each unit lattice. The constructed 3D geotechnical layer map was evaluated by comparing the results of a geostatistical interpolation technique and the topsoil properties of the geological map.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.1
• /
• pp.170-181
• /
• 2015

A research on extracting croplands located nearby coastal areas using the spatial information data sets is the important task for managing the agricultural products in coastal areas. This research aims to extract the various croplands(croplands on mountains and croplands on plain areas) located nearby coastal areas using the KOMPSAT-2 imagery, the high-resolution satellite imagery, and the airborne topographic LiDAR(Light Detection And Ranging) data acquired in coastal areas of Uljin, Korea. Firstly, the NDVI(Normalized Difference Vegetation Index) imagery is generated from the KOMPSAT-2 imagery, and the vegetation areas are extracted from the NDVI imagery by using the appropriate threshold. Then, the DSM(Digital Surface Model) and DEM(Digital Elevation Model) are generated from the LiDAR data by using interpolation method, and the CHM(Canopy Height Model) is generated using the differences of the pixel values of the DSM and DEM. Then the plain areas are extracted from the CHM by using the appropriate threshold. The low slope areas are also extracted from the slope map generated using the pixel values of the DEM. Finally, the areas of intersection of the vegetation areas, the plain areas and the low slope areas are extracted with the areas higher than the threshold and they are defined as the croplands located nearby coastal areas. The statistical results show that 85% of the croplands on plain areas and 15% of the croplands on mountains located nearby coastal areas are extracted by using the proposed methodology.

• Journal of Navigation and Port Research
• /
• v.46 no.6
• /
• pp.471-482
• /
• 2022

This study aims to investigate the characteristics of wave generation in a deep ocean engineering basin and to develop a meta-model of the transfer function of the wavemaker that reflects the geometric characteristics of the deep ocean engineering basin. To this end, the two-dimensional frequency domain boundary element method was applied to achieve an efficient analysis that reflects the geometric characteristics of the deep ocean engineering basin. The developed numerical method was validated through comparison with the analytical solution. Numerical analyses were conducted for the boundary value problem of the wavemaker according to various periods and the positions of the movable bottom. The numerical results were used to investigate the effect of the geometric characteristics of the deep ocean engineering basin on the transfer function of the wavemaker, and the effect of depth on wave generation was checked by changing the position of the movable bottom. To efficiently utilize the various results of the boundary element method, a meta-model, an approximate model of the transfer function of the wave maker, was developed using a thin plate spline interpolation model. The validity of the developed meta-model was confirmed through a comparison of the results of the model tests.