• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.3136-3150
• /
• 2015

A vision-based 3D tracking of articulated human hand is one of the major issues in the applications of human computer interactions and understanding the control of robot hand. This paper presents an improved approach for tracking and recovering the 3D position and orientation of a human hand using the Kinect sensor. The basic idea of the proposed method is to solve an optimization problem that minimizes the discrepancy in 3D shape between an actual hand observed by Kinect and a hypothesized 3D hand model. Since each of the 3D hand pose has 23 degrees of freedom, the hand articulation tracking needs computational excessive burden in minimizing the 3D shape discrepancy between an observed hand and a 3D hand model. For this, we first created a 3D hand model which represents the hand with 17 different parts. Secondly, Random Forest classifier was trained on the synthetic depth images generated by animating the developed 3D hand model, which was then used for Haar-like feature-based classification rather than performing per-pixel classification. Classification results were used for estimating the joint positions for the hand skeleton. Through the experiment, we were able to prove that the proposed method showed improvement rates in hand part recognition and a performance of 20-30 fps. The results confirmed its practical use in classifying hand area and successfully tracked and recovered the 3D hand pose in a real time fashion.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.1
• /
• pp.34-40
• /
• 2005

In this paper, we describe the modeling for the 3D robot laser scanning system consisting of a laser stripe projector, camera, and 5-DOF robot and propose its calibration method. Nonlinear radial distortion in the camera model is considered for improving the calibration accuracy. The 3D range data is calculated using the optical triangulation principle which uses the geometrical relationship between the camera and the laser stripe plane. For optimal estimation of the system model parameters, real-coded genetic algorithm is applied in the calibration process. Experimental results show that the constructed system is able to measure the 3D position within about 1mm error. The proposed scheme could be applied to the kinematically dissimilar robot system without losing the generality and has a potential for recognition for the unknown environment.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.1
• /
• pp.70-74
• /
• 2008

In the field of camera motion research, it is widely held that the position (movement) and pose (rotation) of cameras are correlated and cannot be independently separated. A new equation based on inner product is proposed here to independently separate the position and pose. It is proved that the position and pose are not correlated and the equation is applied to estimation of the camera exterior parameters using a real image and 3D data.

• Journal of Biomedical Engineering Research
• /
• v.29 no.6
• /
• pp.431-435
• /
• 2008

Quantitative information of a three dimensional(3D) kinematics of joint is very useful in knee joint surgery, understanding how knee kinematics related to joint injury, impairment, surgical treatment, and rehabilitation. In this paper, an automated 2D/3D image matching technique was developed to estimate the 3D in vivo knee kinematics using dual X-ray images. First, a 3D geometric model of the knee was reconstructed from CT scan data. The 3D in vivo position and orientation of femoral and tibial components of the knee joint could be estimated by minimizing the pixel by pixel difference between the projection images from the developed 3D model and the given X-ray images. The accuracy of the developed technique was validated by an experiment with a cubic phantom. The present 2D/3D image matching technique for the estimation of in vivo joint kinematics could be useful for pre-operative planning as well as post-operative evaluation of knee surgery.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.1
• /
• pp.47-59
• /
• 2014

This paper deals with a vision-based trajectory tracking control system for a quadrotor-type UAV for entertainment purpose in indoor environment. In contrast to outdoor flights that emphasize the autonomy to complete special missions such as aerial photographs and reconnaissance, indoor flights for entertainment require trajectory following and hovering skills especially in precision and stability of performance. This paper proposes a trajectory tracking control system consisting of a motion generation module, a pose estimation module, and a trajectory tracking module. The motion generation module generates a sequence of motions that are specified by 3-D locations at each sampling time. In the pose estimation module, 3-D position and orientation information of a quadrotor is estimated by recognizing a circular ring pattern installed on the vehicle. The trajectory tracking module controls the 3-D position of a quadrotor in real time using the information from the motion generation module and pose estimation module. The proposed system is tested through several experiments in view of one-point, multi-points, and trajectory tracking control.

• Journal of Ocean Engineering and Technology
• /
• v.19 no.2 s.63
• /
• pp.74-81
• /
• 2005

A 3-D localization method of an autonomous underwater vehicle (AUV) has been developed, which can solve the limitations oj the conventional localization, such as LBL or SBL that reduces the flexibility and availability of the AUV. The system is composed of a mother ship (small unmanned marine prober) on the surface of the water and an unmanned underwater vehicle in the water. The mother ship is equipped with a digital compass and a GPS for position information, and an extended Kalman filter is used for position estimation. For the localization of the AUV, we used only non-inertial sensors, such as a digital compass, a pressure sensor, a clinometer, and ultrasonic sensors. From the orientation and velocity information, a priori position of the AUV is estimated by applying the dead reckoning method. Based on the extended Kalman filter algorithm, a posteriori position of the AUV is, then, updated by using the distance between the AUV and a mother ship on the surface of the water, together with the depth information from the pressure sensor.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.2
• /
• pp.79-88
• /
• 2004

Gaze detection is to locate the position on a monitor screen where a user is looking by computer vision. Gaze detection systems have numerous fields of application. They are applicable to the man-machine interface for helping the handicapped to use computers and the view control in three dimensional simulation programs. In our work, we implement it with a computer vision system setting a IR-LED based single camera. To detect the gaze position, we locate facial features, which is effectively performed with IR-LED based camera and SVM(Support Vector Machine). When a user gazes at a position of monitor, we can compute the 3D positions of those features based on 3D rotation and translation estimation and affine transform. Finally, the gaze position by the facial movements is computed from the normal vector of the plane determined by those computed 3D positions of features. In addition, we use a trained neural network to detect the gaze position by eye's movement. As experimental results, we can obtain the facial and eye gaze position on a monitor and the gaze position accuracy between the computed positions and the real ones is about 4.8 cm of RMS error.

• Journal of KIBIM
• /
• v.13 no.4
• /
• pp.64-73
• /
• 2023

This study introduces a method of estimating the 3D coordinates of structural damage from the detection results of visual inspection provided in 2D image coordinates using sensing data of UAV and 3D shape information of BIM. This estimation process takes place in a virtual space and utilizes the BIM model, so it is possible to immediately identify which member of the structure the estimated location corresponds to. Difference from conventional structural damage localization methods that require 3D scanning or additional sensor attachment, it is a method that can be applied locally and rapidly. Measurement accuracy was calculated through the distance difference between the measured position measured by TLS (Terrestrial Laser Scanner) and the estimated position calculated by the method proposed in this study, which can determine the applicability of this study and the direction of future research.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.765-774
• /
• 2019

In this paper, we propose a point cloud matching algorithm for multiple RGB-D cameras. In general, computer vision is concerned with the problem of precisely estimating camera position. Existing 3D model generation methods require a large number of cameras or expensive 3D cameras. In addition, the conventional method of obtaining the camera external parameters through the two-dimensional image has a large estimation error. In this paper, we propose a method to obtain coordinate transformation parameters with an error within a valid range by using depth image and function optimization method to generate omni-directional three-dimensional model using 8 low-cost RGB-D cameras.

• Journal of Korea Multimedia Society
• /
• v.10 no.6
• /
• pp.716-725
• /
• 2007

In this paper we describe a motion tracking algorithm for 3D human animation using stereo vision system. This allows us to extract the motion data of the end effectors of human body by following the movement through segmentation process in HIS or RGB color model, and then blob analysis is used to detect robust shape. When two hands or two foots are crossed at any position and become disjointed, an adaptive algorithm is presented to recognize whether it is left or right one. And the real motion is the 3-D coordinate motion. A mono image data is a data of 2D coordinate. This data doesn't acquire distance from a camera. By stereo vision like human vision, we can acquire a data of 3D motion such as left, right motion from bottom and distance of objects from camera. This requests a depth value including x axis and y axis coordinate in mono image for transforming 3D coordinate. This depth value(z axis) is calculated by disparity of stereo vision by using only end-effectors of images. The position of the inner joints is calculated and 3D character can be visualized using inverse kinematics.