• Convergence Security Journal
• /
• v.22 no.2
• /
• pp.105-114
• /
• 2022

This paper is presents an intelligent control system that visualizes the direction of arrival for hearing impaired using personal mobility, and aims to recognize and prevent dangerous situations caused by sound such as alarm sounds and crack sounds on roads. The position estimation method of sound source uses a machine learning classification model characterized by generalized correlated phase transformation based on time difference of arrival. In the experimental environment reproducing the road situations, four classification models learned after extracting learning data according to wind speeds 0km/h, 5.8km/h, 14.2km/h, and 26.4km/h were compared with grid search cross validation, and the Muti-Layer Perceptron(MLP) model with the best performance was applied as the optimal algorithm. When wind occurred, the proposed algorithm showed an average performance improvement of 7.6-11.5% compared to the previous studies.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.389-395
• /
• 2022

Because of improvement of deep learning techniques, deep learning using computer vision such as classification, detection and segmentation has also been used widely at many fields. Expecially, automatic driving is one of the major fields that applies computer vision systems. Also there are a lot of works and researches to combine multiple tasks in a single network. In this study, we propose the network that predicts the individual depth of pedestrians and vehicles. Proposed model is constructed based on YOLOv3 for object detection and Monodepth for depth estimation, and it process object detection and depth estimation consequently using encoder and decoder based on hard parameter sharing. We also used attention module to improve the accuracy of both object detection and depth estimation. Depth is predicted with monocular image, and is trained using self-supervised training method.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.11b
• /
• pp.287-290
• /
• 2002

본 논문에서는 디지털 컨텐츠 저작권 보호를 위해 강인성과 비가시성의 유지를 위한 보다 효과적인 방법으로 웨이브릿 변환에서 적응적 워터마크 삽입강도를 갖는 지각적 데이터 은닉 모델을 제안한다. 먼저 영상을 9/7 쌍직교 웨이브릿 필터를 사용해 4레벨로 다해상도 분해한다. 다음으로 연속부대역 양자화(successive subband quantization)를 통한 시각적 중요계수(perceptually significant coefficient: PSC)들을 선정하여 선택된 계수들에 대해서만 워터마크 정보를 삽입한다. 지각 모델은 정상상태의 일반화 가우시안 모델(generalized gaussian model)로 추정된 NVF(noise visibility function)로 에지와 텍스쳐영역 그리고 평탄영역에 따라 각각 적응적으로 삽입되게 한다. 이는 각 서브밴드 내의 분산과 형상계수(shape parameter)에 의해 결정된다. 적응적 워터마크의 삽입강도를 갖기 위해 에지와 텍스쳐영역의 삽입강도는 각 서브밴드의 주파수 감도(frequency sensitivity)로 결정되고, 평탄영역의 삽입강도는 영상의 국부적 특성에 근거한 통계적 가중치를 사용한다. 삽입되는 워터마크는 랜덤시퀀스로 N(0,1)이다. 여러 가지 공격에 대한 실험으로 제안한 방법의 비가시성과 강인성을 확인한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.4
• /
• pp.519-525
• /
• 2007

With the high interest on robot technology and application, the research on artificial auditory systems for robot is very active. In this paper we discuss sound source localization and tracing based on audio-visual information. For video signals we use face detection based on skin color model. Also, binaural-based DOA is used as audio information. We integrate both informations using Kalman filter. The experimental results show that audio-visual person tracking Is useful, specially in the case that some informations are not observed.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.20 no.2
• /
• pp.202-209
• /
• 2014

In this paper, a developed device for detecting target's location and avoiding collision is proposed. Velocity and acceleration model of target are derived to estimate target's information, i.e. position, velocity and acceleration considering process and measurement noise. Kalman filtering method applied to the estimation process and its results was confirmed by simulation. The distance measurements system using laser sensor for moving target system is also developed to confirm the effectiveness of the proposed scheme. Experiments to get information of moving target with velocity and acceleration model was executed. The data with filtering and without filtering was compared by experiments. Discontinuous measured data was changed to smooth and continuous data by Kalman filtering. It is confirmed that desired data was obtained by applying proposed scheme. UI for measuring and monitoring the target data is developed and visual and auditory alarm function is attached on the system Finally, position estimation system of moving target with good performance is achieved by low price equipments.

• Journal of Navigation and Port Research
• /
• v.47 no.1
• /
• pp.10-17
• /
• 2023

A series of studies on the development of autonomous surface ships have been promoted in domestic and foreign countries. One of the main technologies for the development of autonomous ships is path-following control, which is closely related to securing the safety of ships at sea. In this regard, the path-following performance of an autonomous ship should be first evaluated at the design stage. The main aim of this study was to develop a visual and quantitative evaluation method for the path-following control performance of an autonomous ship at the design stage. This evaluation technique was developed using a computational fluid dynamics (CFD)-based path-following control model together with a line-of-sight (LOS) guidance algorithm. CFD software was utilized to visualize waves around the ship, performing path-following control for visual evaluation. In addition, a quantitative evaluation was carried out using the difference between the desired and estimated yaw angles, as well as the distance difference between the planned and estimated trajectories. The results demonstrated that the ship experienced large deviations from the planned path near the waypoints while changing its course. It was also found that the fluid phenomena around the ship could be easily identified by visualizing the flow generated by the ship. It is expected that the evaluation method proposed in this study will contribute to the visual and quantitative evaluation of the path-following performance of autonomous ships at the design stage.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.10B
• /
• pp.1902-1911
• /
• 1999

In this paper we present a content-based image retrieval algorithm using the visual feature vectors which describe the spatial characteristics of objects. The proposed technique uses the Gaussian mixture model(GMM) to represent multi-colored objects and the expectation maximization(EM) algorithm is employed to estimate the maximum likelihood(ML) parameters of the model. After image segmentation is performed based on GMM, the shape and color features are extracted from each object using Fourier descriptors and color histograms, respectively. Image retrieval consists of two steps: first, the shape-based query is carried out to find the candidate images whose objects have the similar shapes with the query image and second, the color-based query is followed. The experimental results show that the proposed algorithm is effective in image retrieving by using the spatial and visual features of segmented objects.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.6
• /
• pp.746-753
• /
• 2008

In this paper, we introduce the improved control method are communicated between a master and a slave robot in the teleoperation systems. When the master and slave robots are located in different places, time delay is unavoidable under the network environment and it is well known that the system can become unstable when even a small time delay exists in the communication channel. The time delay may cause instability in teleoperation systems especially if those systems include haptic feedback. This paper presents a control scheme based on the estimator with virtual master model in teleoperation systems over the network. As the behavior of virtual model is tracking the one of master model, the operator can control real master robot by manipulating the virtual robot. And LQG/LTR scheme was adopted for the compensation of un-modeled dynamics. The approach is based on virtual master model, which has been implemented on a robot over the network. Its performance is verified by the computer simulation and the experiment.

• Journal of the Korea Computer Industry Society
• /
• v.4 no.4
• /
• pp.553-560
• /
• 2003

Can presume number of software failure or remaining fault that is expected with test data that is collected by decided time using SRGM that is studied until present. Therefore, can forecast software reliability achievement degree and software reliability use step. But, reliability evaluation according to if choose any model can change. Therefore, we present SRGM that consider test cost to error detection and error delete cost as SRGM that consider error delete cost in this research. Using this SRGM, can presume number of remaining fault in software, reliability and optimal release time.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.5
• /
• pp.15-24
• /
• 2020

We present a supervised learning method that estimates the simulation parameters required to simulate the fabric from the static drape shape of a given fabric sample. The static drape shape was inspired by Cusick's drape, which is used in the apparel industry to classify fabrics according to their mechanical properties. The input vector of the training model consists of the feature vector extracted from the static drape and the density value of a fabric specimen. The output vector consists of six simulation parameters that have a significant influence on deriving the corresponding drape result. To generate a plausible and unbiased training data set, we first collect simulation parameters for 400 knit fabrics and generate a Gaussian Mixed Model (GMM) generation model from them. Next, a large number of simulation parameters are randomly sampled from the GMM model, and cloth simulation is performed for each sampled simulation parameter to create a virtual static drape. The generated training data is fitted with a log-linear regression model. To evaluate our method, we check the accuracy of the training results with a test data set and compare the visual similarity of the simulated drapes.