• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.735-739
• /
• 2005

This paper presents a new system to estimate the head pose of human in interactive indoor environment that has dynamic illumination change and large working space. The main idea of this system is to suggest a new morphological feature for estimating head angle from stereo disparity map. When a disparity map is obtained from stereo camera, the matching confidence value can be derived by measurements of correlation of the stereo images. Applying a threshold to the confidence value, we also obtain the specific morphology of the disparity map. Therefore, we can obtain the morphological shape of disparity map. Through the analysis of this morphological property, the head pose can be estimated. It is simple and fast algorithm in comparison with other algorithm which apply facial template, 2D, 3D models and optical flow method. Our system can automatically segment and estimate head pose in a wide range of head motion without manual initialization like other optical flow system. As the result of experiments, we obtained the reliable head orientation data under the real-time performance.

• 제어로봇시스템학회논문지
• /
• 제21권9호
• /
• pp.818-826
• /
• 2015

This paper presents a novel methodology for estimating vehicle ego-motion, i.e. tri-axis linear velocities and angular velocities by using stereo vision sensor and 2G1Y sensor (longitudinal acceleration, lateral acceleration, and yaw rate). The estimated ego-motion information can be utilized to predict future ego-path and improve the accuracy of 3D coordinate of obstacle by compensating for disturbance from vehicle movement representatively for collision avoidance system. For the purpose of incorporating vehicle dynamic characteristics into ego-motion estimation, the state evolution model of Kalman filter has been augmented with lateral vehicle dynamics and the vanishing point estimation has been also taken into account because the optical flow radiates from a vanishing point which might be varied due to vehicle pitch motion. Experimental results based on real-world data have shown the effectiveness of the proposed methodology in view of accuracy.

• 대한기계학회논문집A
• /
• 제25권2호
• /
• pp.323-329
• /
• 2001

In this paper, we present a collaborative method for material delivery using a distributed vehicle agents system. Generally used AGV(Autonomous Guided Vehicle) systems in FA require extraordinary facilities like guidepaths and landmarks and have numerous limitations for application in different environments. Moreover in the case of controlling multi vehicles, the necessity for developing corporation abilities like loading and unloading materials between vehicles including different types is increasing nowadays for automation of material flow. Thus to compensate and improve the functions of AGV, it is important to endow vehicles with the intelligence to recognize environments and goods and to determine the goal point to approach. In this study we propose an interaction method between hetero-type vehicles and adaptive fuzzy logic controllers for sensor-based path planning methods and material identifying methods which recognizes color. For the purpose of carrying materials to the goal, simple color sensor is used instead vision system to search for material and recognize its color in order to determine the goal point to transfer it to. The proposed method reaveals a great deal of improvement on its performance.

• 한국정밀공학회지
• /
• 제18권5호
• /
• pp.42-49
• /
• 2001

In This paper, we present a collaborative method for material delivery using a distributed vehicle agents system. Generally used AGV(Autonomous Guided Vehicle) systems in FA(Factory Automation) require extraordinary facilities like guidepaths and landmarks and have numerous limitations for application in different environments. Moreover in the case of controlling multi vehicles, the necessity for developing corporation abilities like loading and unloading materials between vehicles including different types is increasing nowadays for automation of material flow. Thus to compensate and improve the functions of AGV, it is important to endow vehicles with the intelligence to recognize environments and goods and to determine the goal point to approach. In this study we propose an interaction method between hetero-type vehicles and adaptive fuzzy logic controllers for sensor-based path planning methods and material identifying methods which recognizes color. For the purpose of carrying materials to the goal, simple color sensor is used instead of intricate vision system to search for material and recognize its color in order to determine the goal point to transfer it to. The technique for the proposed method will be demonstrated by experiment.

• 반도체디스플레이기술학회지
• /
• 제7권1호
• /
• pp.29-34
• /
• 2008

In this paper, the DE(double erosion) cathode for the reactive magnetron sputtering system is developed for high deposition rate and high target utilization efficiency. The utilization efficiency of the developed DE cathode is 22% higher than that of normal SE(single erosion) cathode. Sputtering process for the nickel oxide thin films with the DE cathode is performed under the following conditions; power with $1kW{\sim}3kW$, pressure with 4mtorr and 8mtorr, oxygen flow ratio with $0%{\sim}80%$. As a result, the hysteresis phenomenon of discharge voltage in 4mtorr is lower than that in 8mtorr and the hysteresis phenomenon of discharge voltage is getting lower as the applied power is getting higher. The structure of cross section and surface roughness of the thin films are observed by FE-SEM and AFM. The structure of cross section of the thin films is columnar and the average surface roughness under oxygen flow ratio of 0%, 52.5% and 65.0% are $2.08{\AA}$, $2.20{\AA}$ and $0.854{\AA}$, respectively.

• Journal of Computing Science and Engineering
• /
• 제2권1호
• /
• pp.98-108
• /
• 2008

Terrain reconstruction from images is an ill-posed, yet commonly desired Structure from Motion task when compositing visual effects into live-action photography. These surfaces are required for choreography of a scene, casting physically accurate shadows of CG elements, and occlusions. We present a novel framework for generating the geometry of landscapes from extremely noisy point cloud datasets obtained via limited resolution techniques, particularly optical flow based vision algorithms applied to live-action video plates. Our contribution is a new statistical approach to remove erroneous tracks ('outliers') by employing a unique combination of well established techniques-including Gaussian Mixture Models (GMMs) for robust parameter estimation and Radial Basis Functions (REFs) for scattered data interpolation-to exploit the natural constraints of this problem. Our algorithm offsets the tremendously laborious task of modeling these landscapes by hand, automatically generating a visually consistent, camera position dependent, thin-shell surface mesh within seconds for a typical tracking shot.

• International Journal of Contents
• /
• 제1권1호
• /
• pp.10-15
• /
• 2005

As the computer becomes a trend, interactive multimedia design can be one media to communicate the cultural knowledge. A folktale can be a powerful material to show a country's culture. In this project, we try to make the folktale content to be understood easily by implementing some cultural information background. The main aim of this project is to give a vision of the richness culture through the interactive multimedia technology. In this paper, we would like to show a flow map content, a streaming of design process and a visual interface design prototype. Finally, interactive multimedia design content is very useful for a transferring the richness culture because people tend to like a multimedia content. In order to make an effective interactive multimedia design content based on a cultural background, a designer should need to understand about users, culture, technology and the whole design process.

• 한국군사과학기술학회지
• /
• 제9권4호
• /
• pp.114-119
• /
• 2006

Data post-processing programs are used for analysis and visualization of the data obtained from computational fluid methods or flow field experiments. In this paper 3D data visualization system which combines a data visualization program with position tracking system using stereo cameras is introduced. This system offers virtual environment for visualization and analysis of three dimensional data.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.63.6-63
• /
• 2001

For robot navigation and visual reconstruction , structure from motion (SFM) is an active issue in computer vision community and its properties are also becoming well understood. As a drawback in SFM, it is well known that the SFM methods, using small motion model such as optical flow and direct method, have inevitably motion ambiguity between translation and rotation, which is called bas-relief ambiguity. In this paper based on the robust direct method using stereo image sequence, we present a new method for improving those ambiguities. Basically, the direct method uses nearly all image pixels for estimating motion parameters and depths, and global optimization techniques are adopted for finding its solution ...

• Ocean Systems Engineering
• /
• 제7권1호
• /
• pp.39-51
• /
• 2017

Fishes detect various sensory stimuli, which may be used to direct their behavior. Especially, the visual and water flow detection information are critical for locating prey, predators, and school formation. In this study, we examined the specific role of these two different type of stimulation (vision and vibration) during the obstacle avoidance behavior of carp, Cyprinus carpio. When a visual obstacle was presented, the carp efficiently turned and swam away in the opposite direction. In contrast, vibration stimulation of the left or right side with a vibrator did not induce strong turning behavior. The vibrator only regulated the direction of turning when presented in combination with the visual obstacle. Our results provide first evidence on the innate capacity that dynamically coordinates visual and vibration signals in fish and give insights on the novel modulation method of fish behavior without training.