• The KIPS Transactions:PartB
• /
• v.10B no.2
• /
• pp.135-142
• /
• 2003

Robust extraction of 3D object's features, shape and global motion information from 2D image sequence is described. The object's 21 feature points on the pyramid type synthetic object are extracted automatically using color transform technique. The extracted features are used to recover the 3D shape and global motion of the object using stereo paraperspective camera model and sequential SVD(Singuiar Value Decomposition) factorization method. An inherent error of depth recovery due to the paraperspective camera model was removed by using the stereo image analysis. A 30 synthetic object with 21 features reflecting various position was designed and tested to show the performance of proposed algorithm by comparing the recovered shape and motion data with the measured values.

• Journal of Electrical Engineering and information Science
• /
• v.1 no.2
• /
• pp.77-86
• /
• 1996

In this paper we deal with the problem of recovering 3-D motion and structure from a time-varying 2-D velocity vector field. A great deal has been done on this topic, most of which has concentrated on finding necessary and sufficient conditions for there to be a unique 3-D solution corresponding to a given 2-D motion. While previous work provides useful theoretical insight, in most situations the known algorithms have turned out to be too sensitive to be of much practical use. It appears that any robust algorithm must improve the 3-D solutions over time. As a step toward such algorithm, we present a method for recovering 3-D motion and structure from a given time-varying 2-D velocity vector field. The surface of the object in the scene is assumed to be locally planar. It is also assumed that 3-D velocity vectors are piecewise constant over three consecutive frames (or two snapshots of flow field). Our formulation relates 3-D motion and object geometry with the optical flow vector as well as its spatial and temporal derivatives. The linearization parameters, or equivalently, the first-order flow approximation (in space and time) is sufficient to recover rigid body motion and local surface structure from the local instantaneous flow field. We also demonstrate, through a sensitivity analysis carried out for synthetic and natural motions in space, that 3-D motion can be recovered reliably.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1629-1632
• /
• 2003

A technique is presented for generating a compound human motion from its primitive motions obtained by a motion capture system. Some human fundamental motions are modeled in a 3-D way and registered as primitive motions. Because the factorization method is used for the motion capture, calibration of video cameras and connection of the motion in the direction of time is both unnecessary. Employing these motions, various compound human motions are generated by connecting the motions after having applied rotation and parallel transformation to them. Linear interpolation is done at the discontinuous boundary between primitive motions and smooth connection is achieved. Experimental results show satisfactory performance of the proposed technique. The technique may contribute to producing various complicated human motions without much effort using a strict motion capture system.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.563-570
• /
• 2002

Robust extraction of 3D facial features and global motion information from 2D image sequence for the MPEG-4 SNHC face model encoding is described. The facial regions are detected from image sequence using multi-modal fusion technique that combines range, color and motion information. 23 facial features among the MPEG-4 FDP (Face Definition Parameters) are extracted automatically inside the facial region using color transform (GSCD, BWCD) and morphological processing. The extracted facial features are used to recover the 3D shape and global motion of the object using paraperspective camera model and SVD (Singular Value Decomposition) factorization method. A 3D synthetic object is designed and tested to show the performance of proposed algorithm. The recovered 3D motion information is transformed into global motion parameters of FAP (Face Animation Parameters) of the MPEG-4 to synchronize a generic face model with a real face.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.5
• /
• pp.347-356
• /
• 2003

Camera pose and scene geometry estimation from video sequences is widely used in various areas such as image composition. Structure and motion recovery based on the auto calibration algorithm can insert synthetic 3D objects in real but un modeled scenes and create their views from the camera positions. However, most previous methods require bundle adjustment or non linear minimization process [or more precise results. This paper presents a new auto' calibration algorithm for video sequence based on two steps: the one is key frame selection, and the other removes the key frame with inaccurate camera matrix based on an absolute quadric estimation by LMedS. In the experimental results, we have demonstrated that the proposed method can achieve a precise camera pose estimation and scene geometry recovery without bundle adjustment. In addition, virtual objects have been inserted in the real images by using the camera trajectories.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.7 no.2
• /
• pp.47-54
• /
• 2013

In this paper, we present an inertial sensor-based motion capturing system to measure and analyze whole body movements. This system implements a wireless AHRS(attitude heading reference system) we developed using a combination of rate gyroscope, accelerometer and magnetometer sensor signals. Several AHRS modules mounted on segments of the patient's body provide the quaternions representing the patient segments's orientation in space. We performed 3D motion capture using the quaternion data calculated. And a method is also proposed for calculating three-dimensional inter-segment joint angle which is an important bio-mechanical measure for a variety of applications related to rehabilitation. To evaluate the performance of our AHRS module, the Vicon motion capture system, which offers millimeter resolution of 3D spatial displacements and orientations, is used as a reference. The evaluation resulted in a RMSE of 2.56 degree. The results suggest that our system will provide an in-depth insight into the effectiveness, appropriate level of care, and feedback of the rehabilitation process by performing real-time limbs or gait analysis during the post-stroke recovery process.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.3
• /
• pp.176-184
• /
• 1998

We present a sequential factorization method using singular value decomposition (SVD) for recovering both the three-dimensional shape of an object and the motion of camera from a sequence of images. We employ paraperpective projection [6] for camera model to handle significant translational motion toward the camera or across the image. The proposed mthod not only quickly gives robust and accurate results, but also provides results at each frame becauseit is a sequential method. These properties make our method practically applicable to real time applications. Considerable research has been devoted to the problem of recovering motion and shape of object from image [2] [3] [4] [5] [6] [7] [8] [9]. Among many different approaches, we adopt a factorization method using SVD because of its robustness and computational efficiency. The factorization method based on batch-type computation, originally proposed by Tomasi and Kanade [1] proposed the feature trajectory information using singular value decomposition (SVD). Morita and Kanade [10] have extenened [1] to asequential type solution. However, Both methods used an orthographic projection and they cannot be applied to image sequences containing significant translational motion toward the camera or across the image. Poleman and Kanade [11] have developed a batch-type factorization method using paraperspective camera model is a sueful technique, the method cannot be employed for real-time applications because it is based on batch-type computation. This work presents a sequential factorization methodusing SVD for paraperspective projection. Initial experimental results show that the performance of our method is almost equivalent to that of [11] although it is sequential.

• Investigative Magnetic Resonance Imaging
• /
• v.11 no.2
• /
• pp.87-94
• /
• 2007

Purpose: The purpose of this study was to evaluate the usefulness of fast inversion recovery (FIR) and magnetization-prepared three dimensional gradient echo sequence (3D GRE) T1-weighted sequences for neonatal brain imaging compared with spin echo (SE) sequence in a 3T MR unit. Materials and Methods: T1-weighted axial SE, FIR and 3D GRE sequences were evaluated from 3T brain MR imaging in 20 neonates. The signal-to-noise ratio (SNR) of different tissues was measured and contrast-to-noise ratios (CNR) were determined and compared in each of the sequences. Visual analysis was carried out by grading gray-white matter differentiation, myelination, and artifacts. The Wilcoxon signed ranked test was used for evaluation of the statistical significance of CNR differences between the sequences. Results: Among the three sequences, the 3D GRE had the best SNRs. CNRs obtained with FIR and 3D GRE were statistically superior to those obtained with SE; these CNRs were better on the 3D GRE compared to the FIR. Gray to white matter differentiation and myelination were better delineated on the FIR and 3D GRE than the SE. However, motion artifacts were more commonly observed on the 3D GRE and flow-related artifacts of vessels were frequently seen on the FIR. Conclusion: FIR and 3D GRE are valuable alternative T1-weighted sequences to conventional SE imaging of the neonatal brain at 3T providing superior image quality.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.31 no.8
• /
• pp.889-895
• /
• 2007

Quantifying dynamic stability is important to assessment of falling risk or functional recovery for leg injured people. Human locomotion is complex and known to exhibit nonlinear dynamical behaviors. The purpose of this study is to quantify major joints of the body using chaos analysis during walking. Time series of the chaotic signals show how gait patterns change over time. The gait experiments were carried out for ten young males walking on a motorized treadmill. Joint motions were captured using eight video cameras, and then three dimensional kinematics of the neck and the upper and lower extremities were computed by KWON 3D motion analysis software. The correlation dimension and the largest Lyapunov exponent were calculated from the time series to quantify stabilities of the joints. This study presents a data set of nonlinear dynamic characteristics for eleven joints engaged in normal level walking.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.2
• /
• pp.281-288
• /
• 2016

The natural moving objects are the most non-rigid shapes with randomly time-varying deformation, and its types also very diverse. Methods of non-rigid shape reconstruction have widely applied in field of movie or game industry in recent years. However, a realistic approach requires moving object to stick many beacon sets. To resolve this drawback, non-rigid shape reconstruction researches from input video without beacon sets are investigated in multimedia application fields. In this regard, our paper propose novel CPSRF(Chained Partial Stereo Rigid Factorization) algorithm that can reconstruct a non-rigid 3D shape. Our method is focused on the real-time reconstruction of non-rigid 3D shape and motion from stereo 2D video sequences per frame. And we do not constrain that the deformation of the time-varying non-rigid shape is limited by a Gaussian distribution. The experimental results show that the 3D reconstruction performance of the proposed CPSRF method is superior to that of the previous method which does not consider the random deformation of shape.