• Journal of Digital Convergence
• /
• v.17 no.10
• /
• pp.233-242
• /
• 2019

Numerous space perception studies have shown that Euclidean 3-D structure cannot be recovered from binocular stereopsis, motion, combination of stereopsis and motion, or even with combined multiple sources of optical information. Humans, however, have no difficulties to perform the task-specific action despite of poor shape perception. We have applied humans skill and capabilities to artificial intelligence and computer vision but those machines are still far behind from humans abilities. Thus, we need to understand how we perceive depth in space and what information we use to perceive 3-D structure accurately to perform. The purpose of this paper was to review space perception literatures to apply humans abilities to artificial intelligence robots more advanced in future.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.2
• /
• pp.59-68
• /
• 1993

The motion vector estimation and motion boundary detection have been briskly studied since they are an important clue for analysis of object structure and 3-d motion. The purpose of this researches is more exact estimation, but there are two main causes to make inaccurate. The one is the erroneous measurement of gradients in brightness values and the other is the blurring of motion boundries which is caused by the smoothness constraint. In this paper, we analyze the gradient measurement error of conventional methods and propose new technique based on it. When the proposed method is applied to the motion boundary detection in Schunck and motion vector estimation in Horn & Schunck, it is shown to have much better performance than conventional method is some artificial and real image sequences.

• Korean Journal of Artificial Intelligence
• /
• v.9 no.2
• /
• pp.35-40
• /
• 2021

In this paper, many game companies seek better optimization and easy-to-apply logic to prolong the game's lifespan and provide a better game environment for users. Therefore, research will be showing the game's key input response method called RoS (Response of Speed). The purpose of the method is to simultaneously perform various motions with the character showing natural motion without errors even if the character's control key is duplicated. This method is for the developers so they can reduce bugs and development time in future game development. To be used with quickly generating game environments, the new method compares with the popular motion method, so which method is faster and can adapt to diverse games. The paper suggested that the Response of Speed method is a better method for optimizing frames and reducing the number of reacting seconds by showing a faster response and speed). With the method popularity of scrollers, many 2D cross-scroll games follow the formula of Dash, Shoot, Walk, Stay, and Crouch. With the development of game engines, it is becoming easier to implement them. Therefore, although the method presented in the above paper differs from the popular method, it is expected that there will be no great difficulty in applying it to the game because transplantation is easy. In the future, we plan to study to minimize the delay of each connection of the character motion so that the game can be optimized to best.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.1491-1492
• /
• 2011

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.10
• /
• pp.948-956
• /
• 2010

The purpose of this study was to test the effectiveness of a prototype KAFO (Knee-Ankle-Foot Orthosis) powered by two artificial pneumatic muscles during walking. We had previously built powered AFO (Ankle-Foot Orthosis) and KO (Knee Orthosis) and used it effectively in studies on assistance of plantaflexion and knee extension motion. Extending the previous study to a KAFO presented additional challenges related to the assistance of gait motion for rehabilitation training. Five healthy males were performed gait motion on treadmill wearing KAFO equipped with artificial pneumatic muscles to power ankle plantaflexion and knee extension. Subjects walked on treadmill at 1.5 km/h under four conditions without extensive practice: 1) without wearing KAFO, 2) wearing KAFO with artificial muscles turned off, 3) wearing KAFO powered only in plantaflexion under feedforward control, and 4) wearing KAFO powered both in plantaflexion and knee extension under feedforward control. We collected surface electromyography, foot pressure and kinematics of ankle and knee joint. The experimental result showed that a muscular strength of wearing KAFO powered plnatarfexion and knee extension under feedforward control was measured to be lower due to pneumatic assistance and foot pressure of wearing KAFO powered plnatarfexion and knee extension under feedforward control was measured to be greater due to power assistance. In the result of motion analysis, the ankle angle of powered KAFO in terminal stance phase was found a peak value toward plantaflexion and there were difference of maximum knee flexion range among condition 2, 3 and 4 in mid-swing phase. The current orthosis design provided plantaflexion torque of ankle jonit in terminal stance phase and knee extension torque of knee joint in mid-swing phase.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.24 no.1
• /
• pp.9-17
• /
• 2020

The stochastic point-source model has been widely used in generating artificial ground motions, which can be used to develop a ground motion prediction equation and to evaluate the seismic risk of structures. This model mainly consists of three different functions representing source, path, and site effects. The path effect is used to emulate decay in ground motion in accordance with distance from the source. In the stochastic point-source model, the path attenuation effect is taken into account by using the geometrical attenuation effect and the inelastic attenuation effect. The aim of this study is to develop accurate equations of ground motion attenuation in the Korean peninsula. In this study, attenuation was estimated and validated by using a stochastic point source model and observed ground motion recordings for the Korean peninsula.

• Journal of information and communication convergence engineering
• /
• v.11 no.4
• /
• pp.274-281
• /
• 2013

In this study, we consider the challenges in motion planning for automated driving systems. Most of the existing online motion-planning algorithms, which take dynamics into account, find it difficult to operate in an environment with narrow passages. Some of the existing algorithms overcome this by offline preprocessing if environment is known. In this work an online algorithm for motion planning with dynamics in an unknown cluttered environment with narrow passages is presented. It utilizes an idea of hybrid planning with sampling- and discretization-based motion planners, which run simultaneously in a full configuration space and a derived reduced space. The proposed algorithm has been implemented and tested with a real autonomous vehicle. It provides significant improvements in computational time performance over basic planning algorithms and allows the generation of smoother paths than those generated by the recently developed hybrid motion planners.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2006.03a
• /
• pp.133-140
• /
• 2006

This paper addresses a fundamental research subject to complement and improve current domestic design specifications for the strong motion duration criterion and the envelop function of artificial accelerograms that can be applied to the earthquake-proof design of nuclear structures. The criteria for design response spectra and strong motion duration suggested by WRC RG 1.60 and ASCE Standard 4-98 are commonly being used in the profession, and they are first compared with each other and reviewed. By applying 152 real strong earthquake records that are over magnitude of 5 in the rock sites to the strong motion duration criterion in ASCE 4-98, an empirical regression model that predicts the strong motion duration as a function of earthquake magnitude is then developed. Using synthetically generated earthquake time histories for the five cases whose strong motion durations vary from 6 to 15 seconds, a seismic analysis is conducted to identify effects of the strong motion durations on the seismic responses of nuclear structures.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2008.04a
• /
• pp.184-189
• /
• 2008

In this study, an artificial wheel load generation method is proposed to assist practical engineers performing dynamic analysis with simple procedure. To generate an artificial wheel loads from running vehicle, PSD(Power Spectrum Density) profiles of actual wheel load were sampled in terms of various road roughnesses. A detailed truck and bridge models were used for sampling actual wheel load to represent the real motion of moving vehicle. These wheel load profiles were simplified for the artificial wheel load. The simplification of actual wheel load profiles was performed by regression analysis. The result showed that the artificial wheel load well represents the real profiles of wheel load.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.787-790
• /
• 2021

본 논문에서는 최신 모션 인식 기술을 활용하여 골프 스윙 비디오에서 사람의 자세를 추정한 후 다양한 원인으로 오검출된 좌표들을 보정하여 자세 추정의 정확도를 높이는 방법을 제안한다. 기존의 사람 자세 추정 모델은 골프 스윙 데이터에서 오검출, 반전, 불안정성, 미검출의 문제를 보여 정확한 자세 추정을 어렵게 했다. 이를 해결하기 위하여 본 연구에서는 자세 추정시 발생하는 이상치 데이터들을 Bi-LSTM 으로 학습하고 골프 스윙의 특징을 고려한 간단한 규칙을 통하여 이상치 데이터를 효과적으로 검출하고 이를 보정하는 방법을 제안한다. 또한 다양한 실험과 분석을 통하여 제안하는 방법이 골프 스윙 모션에서 사람의 자세를 정확히 추정할 수 있음을 보인다.