• Speech Sciences
• /
• v.11 no.2
• /
• pp.193-210
• /
• 2004

In this paper, we develop a real time lip-synch system that activates 2-D avatar's lip motion in synch with an incoming speech utterance. To realize the 'real time' operation of the system, we contain the processing time by invoking merge and split procedures performing coarse-to-fine phoneme classification. At each stage of phoneme classification, we apply the support vector machine (SVM) to reduce the computational load while retraining the desired accuracy. The coarse-to-fine phoneme classification is accomplished via two stages of feature extraction: first, each speech frame is acoustically analyzed for 3 classes of lip opening using Mel Frequency Cepstral Coefficients (MFCC) as a feature; secondly, each frame is further refined in classification for detailed lip shape using formant information. We implemented the system with 2-D lip animation that shows the effectiveness of the proposed two-stage procedure in accomplishing a real-time lip-synch task. It was observed that the method of using phoneme merging and SVM achieved about twice faster speed in recognition than the method employing the Hidden Markov Model (HMM). A typical latency time per a single frame observed for our method was in the order of 18.22 milliseconds while an HMM method applied under identical conditions resulted about 30.67 milliseconds.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.1
• /
• pp.29-34
• /
• 2015

Brain-computer interface (BCI) is being studied for convenient life in various application fields. The purpose of this study is to investigate a changing electroencephalography (EEG) for precise motion of a robot or an artificial arm. Three subjects who participated in this experiment performed three-task: Grip, Move, Relax. Acquired EEG data was extracted feature data using two feature extraction algorithm (power spectrum analysis and multi-common spatial pattern). Support vector machine (SVM) were applied the extracted feature data for classification. The classification accuracy was the highest at Grip class of two subjects. The results of this research are expected to be useful for patients required prosthetic limb using EEG.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.74-86
• /
• 2006

This paper proposes a robust and computationally efficient algorithm for automatic video object segmentation. For implementing the spatio-temporal segmentation, which aims for efficient combination of the motion segmentation and the color segmentation, an SOM-based hierarchical clustering method in which the segmentation process is regarded as clustering of feature vectors is employed. As results, problems of high computational complexity which required for obtaining exact segmentation results in conventional video object segmentation methods, and the performance degradation due to noise are significantly reduced. A measure of motion vector reliability which employs MRF-based MAP estimation scheme has been introduced to minimize the influence from the motion estimation error. In addition, a noise elimination scheme based on the motion reliability histogram and a clustering validity index for automatically identifying the number of objects in the scene have been applied. A cross projection method for effective object tracking and a dynamic memory to maintain temporal coherency have been introduced as well. A set of experiments has been conducted over several video sequences to evaluate the proposed algorithm, and the efficiency in terms of computational complexity, robustness from noise, and higher segmentation accuracy of the proposed algorithm have been proved.

• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.6
• /
• pp.345-349
• /
• 2013

This paper proposes a simplified generalized residual prediction (GRP) that reduces the computational complexity of spatial scalability in scalable high efficiency video coding (SHVC). GRP is a coding tool to improve the inter prediction by adding a residual signal to the inter predictor. The residual signal was created by carrying out motion compensation (MC) of both the enhancement layer (EL) and up-sampled reference layer (RL) with the motion vector (MV) of the EL. In the MC process, interpolation of the EL and the up-sampled RL are required when the MV of the EL has sub-pel accuracy. Because the up-sampled RL has few high frequency components, interpolation of the up-sampled RL does not give significantly new information. Therefore, the proposed method reduces the computational complexity of the GRP by skipping the interpolation of the up-sampled RL. The experiment on SHVC software (SHM-2.0) showed that the proposed method reduces the decoding time by 10 % compared to conventional GRP. The BD-rate loss of the proposed method was as low as 1.0% on the top of SHM-2.0.

• Journal of Korea Multimedia Society
• /
• v.14 no.12
• /
• pp.1536-1543
• /
• 2011

Video stabilization is a very important step for vision based applications in the vehicular technology because the accuracy of these applications such as obstacle distance estimation, lane detection and tracking can be affected by bumpy roads and oscillation of vehicle. Conventional methods suffer from either the zooming effect which caused by a camera movement or some motion of surrounding vehicles. In order to overcome this problem, we propose a novel video stabilization method using FOE(Focus of Expansion). When a vehicle moves, optical flow diffuses from the FOE and the FOE is equal to an epipole. If a vehicle moves with vibration, the position of the epipole in the two consecutive frames is changed by oscillation of the vehicle. Therefore, we carry out video stabilization using motion vector estimated from the amount of change of the epipoles. Experiment results show that the proposed method is more efficient than conventional methods.

• International Journal of Aeronautical and Space Sciences
• /
• v.1 no.1
• /
• pp.81-91
• /
• 2000

The mechanization of navigation equation is depending on the designer according to the orientation vector relating the body frame to a chosen to inertial and navigation frames for its purposes. This paper considers the appropriate Earth Fixed frame for short range vehicle and develops a mechanization and algorithm for Strapdown Inertial Navigation System(SDINS). This mechanization consists of two parts : translational mechanization and rotational mechanization{attitude determination). The accuracy, availability and performance of this SDINS mechanization are verified on the simulation and the numerical method for integration attitude propagation is compared with a well-known method in a precession motion.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.7
• /
• pp.1674-1684
• /
• 1994

An efficient iterative method is presented for the dynamic analysis of bodies moving on flexible structures. In contrast to traditional approaches, the nominal motion of the body is considered here as an unknown. The correct contact forces between the bodies and the flexible structures are computed by an iterative method reducing the specially defined error vectors to zero, and thus satisfying the constraints between the bodies and the structures. Even thought only simple equations of motions and simple time integrators are adopted, the correct solutions are economically obtained and the Timoshenko paradox is completely resolved. Numerical simulations are conducted demonstrate the accuracy and reliability of the solution and to compare the results with the reference.

• Journal of Korea Multimedia Society
• /
• v.21 no.4
• /
• pp.478-484
• /
• 2018

The choice of the motion features influences the result of the human action recognition method directly. Many factors often influence the single feature differently, such as appearance of the human body, environment and video camera. So the accuracy of action recognition is restricted. On the bases of studying the representation and recognition of human actions, and giving fully consideration to the advantages and disadvantages of different features, the Dense Trajectories(DT) algorithm is a very classic algorithm in the field of behavior recognition feature extraction, but there are some defects in the use of optical flow images. In this paper, we will use the improved Dense Trajectories(iDT) algorithm to optimize and extract the optical flow features in the movement of human action, then we will combined with Support Vector Machine methods to identify human behavior, and use the image in the KTH database for training and testing.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.146-148
• /
• 2007

CMDPS (COMS Meteorological Data Processing System) is the operational meteorological products extraction system for data observed from COMS (Communication, Ocean and Meteorological Satellite) meteorological imager. CMDPS baseline products consist of 16 parameters including cloud information, water vapor products, surface information, environmental products and atmospheric motion vector. Additionally, CMDPS includes the function of calibration monitoring, and validation mechanism of the baseline products. The main objective of CMDPS validation module development is near-real time monitoring for the accuracy and reliability of the whole CMDPS products. Also, its long time validation statistics are used for upgrade of CMDPS such as algorithm parameter tuning and retrieval algorithm modification. This paper introduces the preliminary design on CMDPS validation module.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.1003-1006
• /
• 2002

In machining free-form curves with a machine tool equipped with parallel device, improving contouring accuracy is very important. In this paper, we present contouring control algorithm far parallel machine tool. The relation between the error in Joint space and the error in catesian space is evaluated, and we estimate contouring error vector which efficiently determines the variable gains for the cross coupled control. To show the validity of the algorithm, the contouring control is simulated for free form contour trajectory in cubic parallel machine tool model.