• International Journal of Contents
• /
• v.2 no.1
• /
• pp.5-8
• /
• 2006

This paper describes a new mechanism of detecting object of interest from a noisy image, without using any a-priori knowledge about the target. It employs a parallel set of filters inspired upon biological findings of mammalian vision. In our proposed system, several basic features are extracted directly from original input visual stimuli, and these features are integrated based on their local competitive relations and statistical information. Through integration process, unnecessary features for detecting the target are spontaneously decreased, while useful features are enhanced. Experiments have been performed on a set of computer generated and real images corrupted with noise.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.04b
• /
• pp.371-376
• /
• 1995

Computer vision is applicated to measure the position and orientation of the SMD on 8mm Camcoder PCB and advanced image processing algorithms for high accuracy and real time processing are proposed. Illumination conditions are optimized for the best image formation and a set of LEDs is used as economic illuminator, which is regarded as a summation of many point sources. Conctete optical system is constructed and the performance of the proposed algorithm is verified by several experiments.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.41-44
• /
• 2002

Blind source separation (BSS) is a fundamental problem that is encountered in many practical applications. In most existing methods, stationary sources are considered higher-order statistics is necessary either explicitly or implicitly. But, many natural signals are nonstationary, and it is possible to perform BSS using only second-order statistics. Our method is based on only second order statistics. The algorithms are developed using the gradient descent method in orthogonality constraint and their performance is confirmed by numerical experiments.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1140-1141
• /
• 2007

A method of modeling the Smart Power IC is presented in this paper, which is based on the IC's typical operation characteristics and small signal frequency response data. Using the least square identification, the IC's dynamic mathematical model, which is expressed as transfer function, can be synthesized from the experimentally obtained gain and phase data. The practicability and effectiveness of the method are verified by means of experiments.

• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1250-1260
• /
• 2020

This study proposes a novel deep neural network model that can accurately detect objects and their relationships in an image and represent them as a scene graph. The proposed model utilizes several multimodal features, including linguistic features and visual context features, to accurately detect objects and relationships. In addition, in the proposed model, context features are embedded using graph neural networks to depict the dependencies between two related objects in the context feature vector. This study demonstrates the effectiveness of the proposed model through comparative experiments using the Visual Genome benchmark dataset.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.455-457
• /
• 2020

Recent studies demonstrate that deep learning model is easily biased by trained with unbalanced datasets. For example, the deep network can be trained to make a prediction by background feature instead the real target's feature. For those problem, a measurement called leakage was introduced to digitize this tendency. In this paper, we propose augmentation strategy which are used generally in computer vision problem to remedy this bias problem and we showed a simple augmentation methods have a effect to this task with experiments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1026-1042
• /
• 2020

People are increasingly demanding to experience realistic behavior of virtual characters in computer games. In this article, we build a computer model for simulating a bicycle rider's behavior in a virtual riding system. A method to calculate the speed of a bicycle rider is proposed to improve the reality in a virtual riding system. In this method, the property of physical energy is introduced, and the bicycle-riding speed is calculated in real time according to the relationship between the rider's physical energy and bicycle-riding speed. Then based on the analysis of the behavior of a cyclist in a real competition, various behaviors of the virtual rider are designed and a behavior-tree for the virtual bicycle rider is constructed accordingly. On the basis of these, a virtual riding system is developed. The experiments results show that our system can simulate the behavior of a virtual bicycle rider, and thus encourage exercise on a stationary bicycle.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.15 no.2
• /
• pp.28-34
• /
• 2007

In design stage of vehicles, the application of virtual durability analysis techniques enables us to cut down the necessary time and cost to carry out various physical experiments. In this study, computer simulations of vehicle suspensions were carried out with DADS program including component flexibility, and the durability analysis of vehicle components was executed with MSC/Fatigue program using the load history obtained from vehicle dynamic simulation. Driving test of a vehicle was also carried out to obtain precise input data for the durability analysis, and the results of virtual durability analysis were compared to those of experiments.

• Journal of Biosystems Engineering
• /
• v.17 no.3
• /
• pp.223-228
• /
• 1992

This study was conducted to develop an electro-hydraulic three-point hitch control system using an electro-hydraulic servo valve and microcomputer and to investigate the performance of the three-point hitch control system through indoor and field experiments. 1. The results from indoor experiments coincided with those from computer simulation reported in the previous paper. However, the draft control with the value 4 of Kd showed a slight sustained oscillation after it reached the draft set. 2. From the field experiments, it appeared that the RMS errors increased with the ground speed of tractor. In position control, the three-point hitch control system with electro-hydraulic servo valve showed better performance than that with on-off electro-magnetic valve in the ground speed less than 1.6 m/s. In draft control, however, there was no significant differece in performance between those two systems. 3. In depth control, the both types of electro-hydraulic three-point hitch control system showed better performance than the conventional mechanical-hydraulic three-point hitch control system.

• Proceedings of the KSME Conference
• /
• 2003.04a
• /
• pp.705-710
• /
• 2003

Many papers have studied computer simulations of elastic bodies undergoing large deflections and large deformations. But there have not been many attempts to check the validity of the numerical formulations because the simulation results could not be matched without correct input data such as material properties and damping effects. In this paper, these values are obtained from real experiment with a high-speed camera and a data acquisition system. The simulation results with the absolute nodal coordinate formulation (ANCF) are compared with the results of real experiments. Two examples, a thin cantilever beam and a thin plate, are studied to verify whether the simulation results are well matched to experimental results.