• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.4
• /
• pp.379-384
• /
• 2009

A human gaze detection and tracing method is importantly required for HMI(Human-Machine-Interface) like a Human-Serving robot. This paper proposed a novel three-dimension (3D) human gaze estimation method by using a face recognition, an orientation estimation and SVMs (Support Vector Machines). 2,400 images with the pan orientation range of $-90^{\circ}{\sim}90^{\circ}$ and tilt range of $-40^{\circ}{\sim}70^{\circ}$ with intervals unit of $10^{\circ}$ were used. A stereo camera was used to obtain the global coordinate of the center point between eyes and Gabor filter banks of horizontal and vertical orientation with 4 scales were used to extract the facial features. The experiment result shows that the error rate of proposed method is much improved than Liddell's.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2006.03a
• /
• pp.931-938
• /
• 2006

Using high resolution stereoscopic imaging system three digital elevation model of tunnel face is acquired. The images oriented within a given tunnel coordinate system are brought into a stereoscopic vision system enabling three dimensional inspection and evaluation. The possibilities for the prediction ahead and outside of tunnel face have been improved by the digital vision system with 3D model. Interpolated image structures of rock mass between subsequent stereo images will enable to model the rock mass surrounding the opening within a short time at site. The models shall be used as input to numerical simulations on site, comparison of expected and encountered geological conditions, and for the interpretation of geotechnical monitoring results.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2000.04a
• /
• pp.129-133
• /
• 2000

It is reasonable to use the stereo vision and image processing technique to digitize 3D coordinates of grid points and to evaluate surface strains on a sheet metal parts. However this method has its intrinsic problems such as the difficulty in enhancement of bad images inevitable error due to digital image resolution of camera and frame grabber unreliability of strains and thickness evaluated from coarse grid on the corner area with large curvature and the limitation of the area that can be measured at a time. Therefore it is still hard to measure strain distribution over the entire surface of a medium,- or large-sized stamped part at a time even by using an automated strain measurement system. In this study the curvature correction algorithm based on the grid refinement and the geometry assembling algorithm based on the global error minimization (GEM) scheme are suggested. Several applications are presented to show the reliability and efficiency of these algorithms.

• International Journal of CAD/CAM
• /
• v.9 no.1
• /
• pp.31-36
• /
• 2010

3D point data acquired from laser scan or stereo vision can be quite noisy. A preprocessing step is often needed before a surface reconstruction algorithm can be applied. In this paper, we propose a nonparametric approach for noisy point data preprocessing. In particular, we proposed an anisotropic kernel based nonparametric density estimation method for outlier removal, and a hill-climbing line search approach for projecting data points onto the real surface boundary. Our approach is simple, robust and efficient. We demonstrate our method on both real and synthetic point datasets.

• Proceedings of the KSME Conference
• /
• 2001.06b
• /
• pp.158-163
• /
• 2001

Operators suffer much difficulty in manipulating micro/nano-sized objects without the assistance of human interfaces, due to the scaling effects in micro/nano world. This paper presents a micro manipulation system based on the teleoperation techniques which enables the operators to manipulate the objects with ease by transferring both human motion and manipulation skill to a micromanipulator. An experimental setup consisting of a micromanipulator operated under stereo-microscope with the help of intelligent user interface provides a tool that can be used to visualize and manipulate micro-sized 3D objects in a controlled manner. The key features of a micro manipulation system and control strategies using teleoperation techniques for handling micro objects are presented. Experimental results demonstrate the feasibility of this system in precisely controlling trapping and manipulation of micro objects based on teleoperation techniques.

• Journal of the Korean Geophysical Society
• /
• v.8 no.1
• /
• pp.23-33
• /
• 2005

The digital surface model (DSM) is used for several purposes in photogrammetry, remote sensing and laser scanned data such as orthoimage production, contours erivation, extraction of height information. Creation of a surface model from point-clouds (3-D sparse points) that can be derived from stereo imagery and range data (e.g. laser scanned data) can be done with several mathematical interpolation models. In this paper, thin-plate-spline (TPS) is used for digital surface modeling. Determination of suitable weight is an important problem in thin-plate function for a surface. The Voronoi algorithm has been proposed as a method for determination of the weight in thin-plate-spline. In this paper, methods has been tested for different surfaces. The results show that thin-plate-spline can be independent of weight.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.5
• /
• pp.419-428
• /
• 2011

This paper suggests a judgement method for an inclined plane before entrance of it and the detection of obstacle position. Main idea is started from the assumption that obstacle is always on the bottom plane, and corner appears at this position. The process to detect the obstacle consists of three steps. First the 3D data using stereo matching is acquired to detect an obstacle. Second a bottom plane is extracted by using limit condition. Last the obstacle position is found by using Harris corner detection. Obstacle position detection on an inclined plane was verified by outdoor and indoor experiment. In error analysis, it is confirmed that an average error of obstacle detection in outdoor was larger than the error in indoor but the error are within about 0.030 m. This method will be applied to unmanned vehicles to navigate under various environment.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2941-2943
• /
• 1999

The application of the aerial images are to find the 3-D elevations. Image matching techniques such as Multi-resolution techniques, WCC (Weighted Cross-Correlation), NSSR (Narrow Search Sub-pixel Registration) that we know robustly apply to images which have enough features. But the method is not adaptive in images which have not enough features due to increasing of disparity errors. In this paper, we propose Disparity Interpolation that decrease disparity errors occurring in the area where images have not enough features. By using real aerial images we compare the result from existing image matching techniques to the result from proposed method.

• Journal of Positioning, Navigation, and Timing
• /
• v.10 no.4
• /
• pp.297-305
• /
• 2021

Monocular depth estimation helps the robot to understand the surrounding environments in 3D. Especially, deep-learning-based monocular depth estimation has been widely researched, because it may overcome the scale ambiguity problem, which is a main issue in classical methods. Those learning based methods can be mainly divided into three parts: supervised learning, unsupervised learning, and semi-supervised learning. Supervised learning trains the network from dense ground-truth depth information, unsupervised one trains it from images sequences and semi-supervised one trains it from stereo images and sparse ground-truth depth. We describe the basics of each method, and then explain the recent research efforts to enhance the depth estimation performance.

• Journal of Broadcast Engineering
• /
• v.9 no.3
• /
• pp.196-206
• /
• 2004

This paper presents an efficient joint disparity-motion estimation algorithm for stereo sequence CODEC. Disparity vectors are estimated by the left and right motion vectors and previous disparity vectors for every frame. In order to obtain more accurate disparity vectors. we include a spatial prediction Process after the feint estimation. From joint estimation and spatial prediction, we can obtain accurate disparity vectors and then Increase coding efficiency. Finally, we proposed the backward quadtree decomposition. which helps the encoder to have a more detailed disparity vector map without transmitting additional coding bits for quadtree information. We confirmed superior performance of the proposed method through computer simulation.