• Journal of the Korea Computer Graphics Society
• /
• v.15 no.1
• /
• pp.17-23
• /
• 2009

We present a simple new idea to improve the quality of exemplar based texture synthesis using multiple rotated input exemplars. Our algorithm successfully obtain rotational synthesis feature variations and manages to reduce the artifacts in the results, especially patch seams due to the structure of the exemplars provided which have been inappropriate for previous neighborhood matching synthesis algorithms. Our algorithm is parallel in nature, thus it is possible to implement our algorithm using GPU or multi-core CPU to accelerate synthesis process.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06b
• /
• pp.135-140
• /
• 2008

최근 주변에서 다양한 음악분수를 찾아볼 수 있다. 음악분수의 연출을 위해서는 음악과 동기화되는 물의 움직임을 정의하는 음악분수 시나리오가 요구된다. 하지만 일반적으로 이러한 시나리오는 전문가들에 의하여 생성되기 때문에, 비용적인 문제로 인하여 다양한 음악에 대한 시나리오가 생성되지 못하고 있는 현실이다. 본 논문에서는 예제 기반 방식을 이용하여 자동으로 음악 분수의 시나리오를 생성하는 방법을 제안한다. 즉 기존에 전문가들에 의하여 생성되었던 음악분수의 시나리오를 분석하여 데이터베이스화 시킨 후, 이를 새롭게 합성하여 시나리오를 생성한다. 또한 음악분수 시나리오 생성에서 중요하게 요구되는 음악과 물 모양의 동기화를 위하여 본 논문에서는 임의의 음악이 들어왔을 때, 이 음악의 비트를 추출한 후 비트를 단위로 시나리오를 합성하게 된다. 사용자 실험결과 본 기술에 의하여 자동 생성된 시나리오는 전문가가 생성한 시나리오와 큰 차이가 나지 않음을 알 수 있었다. 본 기술을 이용하면 음악분수 시나리오를 생성할 때 요구되는 시간을 크게 줄일 수 있으며, 이로 인해 음악분수의 유지비용을 크게 절감할 수 있다.

• Journal of the Korea Computer Graphics Society
• /
• v.20 no.2
• /
• pp.25-32
• /
• 2014

We present an example-based approach to synthesizing physically simulated Rube Goldberg machines in which a series of rigid body elements are sequentially triggered and driven along the causal chain. Given a set of elements, our goal is to automatically instantiate and arrange those elements to meet the user-specified requirements including the start and end positions, and the boundary of movement. To do so, we first sample small-scale machines consisting of only a few elements randomly, and represent the connectivity between every pair of components as a graph structure. Searching over possible paths in this graph solves our problem by finding a path that can be unrolled to satisfy the given requirements, and then assembling components sequentially along the solution path. In order to ensure that the machine works precisely in a physically simulated environment, we finally elaborate the layout of assembled components by a simple greedy algorithm. We demonstrate the usefulness of our approach by displaying a large diversity of Rube Goldberg machines built with only five kinds of elements.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.371-375
• /
• 2008

예제 기반 학습(instance-based learning) 방법 중 하나인 k-최근접 이웃(k-nearest reighbor, k-NN) 학습은 간단하고 예측 정확도가 비교적 높아 분류 및 회귀 문제 해결을 위한 기반 방법론으로 널리 적용되고 있다. k-NN 학습을 위한 알고리즘은 기본적으로 유클리드 거리 혹은 2-놈(norm)에 기반하여 학습예제들 사이의 거리를 계산한다. 본 논문에서는 유클리드 거리를 일반화한 개념인 p-놈의 사용이 k-NN 학습의 성능에 어떠한 영향을 미치는지 연구하였다. 구체적으로 합성데이터와 다수의 기계학습 벤치마크 문제 및 실제 데이터에 다양한 p-놈을 적용하여 그 일반화 성능을 경험적으로 조사하였다. 실험 결과, 데이터에 잡음이 많이 존재하거나 문제가 어려운 경우에 p의 값을 작게 하는 것이 성능을 향상시킬 수 있었다.

• Journal of Korea Multimedia Society
• /
• v.15 no.4
• /
• pp.508-515
• /
• 2012

This paper presents a method that estimates face pose for a given face image and synthesizes any posed face images using Active Appearance Model(AAM). The AAM that having been successfully applied to various applications is an example-based learning model and learns the variations of training examples. However, with a single model, it is difficult to handle large pose variations of face images. This paper proposes to build a model covering only a small range of angle for each pose. Then, with a proper model for a given face image, we can achieve accurate pose estimation and synthesis. In case of the model used for pose estimation was not trained with the angle to synthesize, we solve this problem by training the linear relationship between the models in advance. In the experiments on Yale B public face database, we present the accurate pose estimation and pose synthesis results. For our face database having large pose variations, we demonstrate successful frontal pose synthesis results.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.780-783
• /
• 2012

Recently, the SoC industry mainly uses various multi-layered bus architectures. However, reckless use of bus layers may results in on-chip communication resources and waste of silicon area. This paper performs a quantitative analysis to compare the two de-facto on-chip buses and SNP. Through the performance estimation, the performance of SNP turns out to be significantly enhanced for asymmetric write and read traffic (non-central F distribution) while symmetric traffic is similar to that of AXI. More specifically, SNP properly places IP cores on the top or bottom, induces the write and read channels to be balanced, and achieves about twenty percent improved performance compared to AXI.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.301-301
• /
• 2022

본 연구는 운영 조건이 달라짐에 따라 회전수가 변하는 기기의 정상적 가동 여부와 고장 종류를 판별하기 위한 인공지능 알고리즘의 적용을 다루고 있다. 회전수가 변하는 장비로부터 계측된 상태 모니터링 센서의 신호는 비정상(non-stationary)적 특성이 있으므로, 상태 신호의 한계치가 고장 판별의 기준이 되기 어렵다는 점을 해결하고자 하였다. 정상 가동 여부는 이상 감지에 효율적인 오토인코더 및 기계학습 알고리즘을 적용하였으며, 고장 종류 판별에는 기계학습법과 합성곱 기반의 심층학습 방법을 적용하였다. 변하는 회전수와 연계된 주파수의 비정상적 시계열도 적절한 고장 특징 (Feature)로 대변될 수 있도록 시간 및 주파수 영역에서 특징 벡터를 구성할 수 있음을 예제로 설명하였다. 차원 축소 및 카이 제곱 기법을 적용하여 최적의 특징 벡터를 추출하여 기계학습의 분류 알고리즘이 비정상적 회전 신호를 가진 장비의 고장 예측에 활용될 수 있음을 보였다. 이 과정에서 k-NN(k-Nearest Neighbor), SVM(Support Vector Machine), Random Forest의 기계학습 알고리즘을 적용하였다. 또한 시계열 기반의 오토인코더 및 CNN (Convolution Neural Network) 적용하여 이상 감지와 고장진단을 수행한 결과를 비교하여 제시하였다.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.439-444
• /
• 2008

The techniques, which locate example motions in abstract parameter space and interpolate them to generate new motion with given parameters, are widely used in real-time animation system for its controllability and efficiency However, as the dimension of parameter space increases for more complex control, the number of example motions for parameterization increases exponentially. This paper proposes a method that uses two different parameter spaces to obtain decoupled control over upper-body and lower-body motion. At each frame time, each parameterized motion space produces a source frame, which satisfies the constraints involving the corresponding body part. Then, the target frame is synthesized by splicing the upper body of one source frame onto the lower body of the other. To generate corresponding source frames to each other, we present a novel scheme for time-warping. This decoupled parameterization alleviates the problems caused by dimensional complexity of the parameter space and provides users with layered control over the character. However, when the examples are parameterized based on their upper body's spatial properties, the parameters of the examples are varied individually with every change of its lower body. To handle this, we provide an approximation technique to change the positions of the examples rapidly in the parameter space.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.7
• /
• pp.10-16
• /
• 1999

In this paper, we propose a concatenation-based speech synthesizer using CVC(consonant-vowel-consonant) speech segments extracted from an undesigned continuous speech corpus. Natural synthetic speech can be generated by a proper modelling of coarticulation effects between phonemes and the use of natural prosodic variations. In general, CVC synthesis unit shows smaller acoustic degradation of speech quality since concatenation points are located in the consonant region and it can properly model the coarticulation of vowels that are effected by surrounding consonants. In this paper, we analyze the characteristics and the number of required synthesis units of 4 types of speech synthesis methods that use CVC synthesis units. Furthermore, we compare the speech quality of the 4 types and propose a new synthesis method based on the most promising type in terms of speech quality and implementability. Then we implement the method using the speech corpus and synthesize various examples. The CVC speech segments that are not in the speech corpus are substituted by demonstrate speech segments. Experiments demonstrate that CVC speech segments extracted from about 100 Mbytes continuous speech corpus can produce high quality synthetic speech.

• Journal of the Korea Society for Simulation
• /
• v.23 no.2
• /
• pp.57-64
• /
• 2014

This paper proposes a framework to construct the synthetic battlefield based aviation engagement simulation model for the distributed system. The proposed framework has the synthetic battlefield in the HLA (High Level Architecture)/RTI (Run-Time Infrastructure) based distributed system to reflect environmental effects into the aviation engagement simulation model. In an aviation engagement, the environment affects weapon systems such as detection and movement. Therefore, environmental effects are required to be reflected in the simulation. However, former researches are inadequate for complex operations of weapon systems that are requirements of the engagement simulation. Thus, the construction of the engagement simulation system of which reflects environmental effects based on environmental data is still difficult. The main objective of this paper is to propose a framework to solve the difficulty and constructs an example system based on the proposed framework.