• Journal of the Korea Convergence Society
• /
• v.9 no.12
• /
• pp.33-38
• /
• 2018

Recently, we are trying to predict the emotion from various information and to convey the emotion information that the supervisor wants to inform the audience. In addition, audiences intend to understand the flow of emotions through various information of non-dialogue parts, such as cinematography, scene background, background sound and so on. In this paper, we propose to extract emotions by mixing not only the context of scripts but also the cinematography information such as color, background sound, composition, arrangement and so on. In other words, we propose an emotional prediction system that learns and distinguishes various emotional expression techniques into dialogue and non-dialogue regions, contributes to the completeness of the movie, and quickly applies them to new changes. The precision of the proposed system is improved by about 5.1% and 0.4%, and the recall is improved by about 4.3% and 1.6%, respectively, when compared with the modified n-gram and morphological analysis.

• Journal of Broadcast Engineering
• /
• v.26 no.3
• /
• pp.258-268
• /
• 2021

Point cloud content is immersive content that represents real-world objects with three-dimensional (3D) points. In the process of acquiring point cloud data or encoding and decoding point cloud data, the resolution of point cloud content could be degraded. In this paper, we propose a method of progressively enhancing the resolution of sequential point cloud contents through inter-frame registration. To register a point cloud, the iterative closest point (ICP) algorithm is commonly used. Existing ICP algorithms can transform rigid bodies, but there is a disadvantage that transformation is not possible for non-rigid bodies having motion vectors in different directions locally, such as point cloud content. We overcome the limitations of the existing ICP-based method by registering regions with motion vectors in different directions locally between the point cloud content of the current frame and the previous frame. In this manner, the resolution of the point cloud content with geometric movement is enhanced through the process of registering points between frames. We provide four different point cloud content that has been enhanced with our method in the experiment.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1037-1044
• /
• 2020

Since radar wind profiler (RWP) provides wind field data with high time and space resolution in all weather conditions, their verification of the accuracy and quality is essential. The simultaneous wind measurement from rawinsonde is commonly used to evaluate wind vectors from RWP. In this study, the simulation algorithm which produces the spectrum and raw time series (I/Q) data from the average values of moments is presented as a step-by-step verification method for the signal processing algorithm. The possibility of the simulation algorithm was also confirmed through comparison with the raw data of LAP-3000. The Doppler power spectrum was generated by assuming the density function of the skew-normal distribution and by using the moment values as the parameter. The simulated spectrum was generated through random numbers. In addition, the coherent averaged I/Q data was generated by random phase and inverse discrete Fourier transform, and raw I/Q data was generated through the Dirichlet distribution.

• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.718-727
• /
• 2022

The Korean domestic cartoon industry has grown explosively by 65% compared to the previous year. Then the market size is expected to exceed KRW 1 trillion. However, excessive work results in health deterioration. Moreover, this working environment makes the production of human resources insufficient, repeating a vicious cycle. Although some tasks require creation activity during cartoon production, there are still a lot of simple repetitive tasks. Therefore, this study aimed to develop a method for creating a character pose through human pose estimation (HPE). The HPE is to detect key points for each joint of a user. The primary role of the proposed method was to make each joint of the character match that of the human. The proposed method enabled us to create the pose of the two-dimensional cartoon character through the results. Furthermore, it was possible to save the static image for one character pose and the video for continuous character pose.

• Journal of Advanced Navigation Technology
• /
• v.26 no.3
• /
• pp.166-171
• /
• 2022

In this paper, we propose an algorithm to improve DoA(direction of arrival) estimation performance of the subspace-based method by generating high robustness correlation matrix of the signals incident on the uniformly linear array antenna. The existing subspace-based DoA estimation method estimates the DoA by obtaining a correlation matrix and dividing it into a signal subspace and a noise subspace. However, the component of the correlation matrix obtained from the low SNR and small number of snapshots inaccurately estimates the signal subspace due to the noise component of the antenna, thereby degrading the DoA estimation performance. Therefore a robust correlation matrix is generated by arranging virtual signal vectors obtained from the existing correlation matrix in a sliding manner. As a result of simulation using MUSIC and ESPRIT, which are representative subspace-based methods,, the computational complexity increased by less than 2.5% compared to the existing correlation matrix, but both MUSIC and ESPRIT based on RMSE 1° showed superior DoA estimation performance with an SNR of 3dB or more.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.741-747
• /
• 2022

Fatigue lowers an individual's ability and makes it difficult to perform work. As fatigue accumulates, concentration decreases and thus the possibility of causing a safety accident increases. Awareness of fatigue is subjective, but it is necessary to quantitatively measure the level of fatigue in the actual field. In previous studies, it was proposed to measure the level of fatigue by expert judgment by adding objective indicators such as bio-signal analysis to subjective evaluations such as multidisciplinary fatigue scales. However this method is difficult to evaluate fatigue in real time in daily life. This paper is a study on the fatigue classification model that determines the fatigue level of workers in real time using speech data recorded in the field. Machine learning models such as logistic classification, support vector machine, and random forest are trained using speech data collected in the field. The performance evaluation showed good performance with accuracy of 0.677 to 0.758, of which logistic classification showed the best performance. From the experimental results, it can be seen that it is possible to classify the fatigue level using speech signals.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.817-826
• /
• 2022

AI technology is being successfully introduced in many fields, and models deployed as a service are deployed with black box environment that does not expose the model's information to protect intellectual property rights and data. In a black box environment, attackers try to steal data or parameters used during training by using model output. This paper proposes a method of inferring the type of model to directly find out the composition of layer of the target model, based on the fact that there is no attack to infer the information about the type of model from the deep learning model. With ResNet, VGGNet, AlexNet, and simple convolutional neural network models trained with MNIST datasets, we show that the types of models can be inferred using the output values in the gray box and black box environments of the each model. In addition, we inferred the type of model with approximately 83% accuracy in the black box environment if we train the big and small relationship feature that proposed in this paper together, the results show that the model type can be infrerred even in situations where only partial information is given to attackers, not raw probability vectors.

• Journal of Internet Computing and Services
• /
• v.24 no.1
• /
• pp.49-59
• /
• 2023

Recently, attention to the pandemic situation represented by COVID-19 emerged problems caused by unexpected shortage of medical personnel. In this paper, we present a method for diagnosing the presence or absence of lesional sign on PA chest X-ray images as computer vision solution to support diagnosis tasks. Method for visual anomaly detection based on feature modeling can be also applied to X-ray images. With extracting feature vectors from PA chest X-ray images and divide to patch unit, region-specific abnormality can be detected. As preliminary experiment, we created simulation data set containing multiple objects and present results of the comparative experiments in this paper. We present method to improve both efficiency and performance of the process through hard masking of patch features to aligned images. By summing up regional specificity and global anomaly detection results, it shows improved performance by 0.069 AUROC compared to previous studies. By aggregating region-specific and global anomaly detection results, it shows improved performance by 0.069 AUROC compared to our last study.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.432-432
• /
• 2023

한국건설기술연구원(Korea Institute of Civil Engineering and Building Technology, KICT)의 안동하천연구센터(Andong River Experiment Center, REC)는 다양한 하천 관련 실규모 실험을 수행하기 위해 3개의 수로를 보유하고 있다. 본 연구의 주목적인 실증 실험 계측 결과를 기반으로 3D 게임엔진을 이용하여 물 흐름을 재현하기 위해 A1 수로를 대상구간으로 설정하였다. 실증 실험의 경우 2개의 수문 개도율 조건에서 ADV와 ADCP를 활용하여 계측된 유량 및 유속 결과들을 비교하였으며, 추가적으로 영상 데이터로 부터 표면유속(LS-PIV)을 산정하였다. 3D 게임 엔진은 렌더링 엔진, 물리 엔진, 오디오 엔진, UI 시스템, 게임플레이 프레임워크 등이 잘 융합된 소스코드들과 개발자들이 이용하기 쉬운 방식으로 변환된 툴(tool)로 제공하여 현실 세계를 가상 세계에 시각화하여 구현하는데 큰 장점을 가지고 있다. 또한 기존의 흐름 재현이 가능한 수리/수문 모델링의 경우 특정한 목적으로만 이용가능하고 연산에 소용되는 시간 때문에 실시간 흐름재현이 어렵지만, 3D 게임엔진을 이용하는 경우 다양한 목적과 여러 분야와의 고려가 동시에 가능하며 연산의 단순화를 통해 실시간 흐름 재현이 가능하다는 장점이 있다. 본 연구에서는 언리얼 엔진의 Niagara Fluids와 Fluid flux 툴들을 활용하여 하천실증실험 시설 일부 구간에 대해 물 흐름을 재현하였다. 먼저 하천실험실증시설을 드론과 RTK-GPS를 이용하여 촬영된 결과를 정합하여 3D 게임엔진 기반 흐름 재현을 위한 지형 기초 자료를 구축하였다. 지형 계측 결과를 기반으로 A1 수로 전체 구간을 대상구간으로 설정한 이후 수문 조절을 통해 흐름 조건을 제어할 수 있도록 제작하였으며, 실제 흐름에 대한 계측 결과를 기반으로 재현된 흐름을 대상으로 material 값의 조정(방향 X, Y값을 RGB값으로 변환한 뒤 벡터 길이 값으로 환산)을 통해 0~100 사이 값을 이용하여 유속을 표현하였다. 최근 가상공간 (i.e. 디지털트윈) 관련 시장 성장이 매우 빠르고 다양한 사업에서 해당 기술의 수요가 증가하고 있으며, 본 연구를 통해 물 흐름의 디지털 트윈화를 위한 수단으로서 3D 게임 엔진의 활용 가능성을 확인하였다. 다만 실제 하천의 적용과 하천관리를 위한 실용화를 위해서는 추가적인 연구와 분석이 이루어져야 할 것이다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.1
• /
• pp.219-232
• /
• 2023

Mobility services need to change according to the regional characteristics of the target service area. Accordingly, analysis of mobility patterns and characteristics based on Origin-Destination (OD) data that reflect travel behaviors in the target service area is required. However, since conventional methods construct the OD data obtained from the administrative district-based zone system, it is hard to ensure spatial homogeneity. Hence, there are limitations in analyzing the inherent travel patterns of each mobility service, particularly for new mobility service like Demand Responsive Transit (DRT). Unlike the conventional approach, this study applies a data-driven clustering technique to conduct spatial analyses on OD travel patterns of regional mobility services based on reconstructed OD data derived from re-aggregation for original OD distributions. Based on the reconstructed OD data that contains information on the inherent feature vectors of the original OD data, the proposed method enables analysis of the spatial characteristics of regional mobility services, including public transit bus, taxi and DRT.