• Journal of Internet Computing and Services
• /
• v.14 no.6
• /
• pp.117-124
• /
• 2013

In this paper, we present a new method which efficiently estimates a face direction from a sequences of input video images in real time fashion. For this work, the proposed method performs detecting the facial region and major facial features such as both eyes, nose and mouth by using the Haar-like feature, which is relatively not sensitive against light variation, from the detected facial area. Then, it becomes able to track the feature points from every frame using optical flow in real time fashion, and determine the direction of the face based on the feature points tracked. Further, in order to prevent the erroneously recognizing the false positions of the facial features when if the coordinates of the features are lost during the tracking by using optical flow, the proposed method determines the validity of locations of the facial features using the template matching of detected facial features in real time. Depending on the correlation rate of re-considering the detection of the features by the template matching, the face direction estimation process is divided into detecting the facial features again or tracking features while determining the direction of the face. The template matching initially saves the location information of 4 facial features such as the left and right eye, the end of nose and mouse in facial feature detection phase and reevaluated these information when the similarity measure between the stored information and the traced facial information by optical flow is exceed a certain level of threshold by detecting the new facial features from the input image. The proposed approach automatically combines the phase of detecting facial features and the phase of tracking features reciprocally and enables to estimate face pose stably in a real-time fashion. From the experiment, we can prove that the proposed method efficiently estimates face direction.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.5
• /
• pp.977-984
• /
• 2007

A realtime face tracking algorithm using motion analysis from image sequences and color information is proposed. Motion area from the realtime moving images is detected by calculating temporal derivatives first, candidate pixels which represent face region is extracted by the fusion filtering with multiple color models, and realtime face tracking is performed by discriminating face components which includes eyes and lips. We improve the stability of face tracking performance by using template matching with face region in an image sequence and the reference template of face components.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.9
• /
• pp.2021-2030
• /
• 2012

Premature ventricular contraction(PVC) is the most common disease among arrhythmia and it may cause serious situations such as ventricular fibrillation and ventricular tachycardia. Particularly, in the healthcare system that must continuously monitor patient's situation, it is necessary to process ECG (Electrocardiography) signal in realtime. In other words, the design of algorithm that exactly detects R wave using minimal computation and classifies PVC by analyzing the persons's physical condition and/or environment is needed. Thus, the patient adaptive pattern matching algorithm for the classification of PVC is presented in this paper. For this purpose, we detected R wave through the preprocessing method, adaptive threshold and window. Also, we applied pattern matching method to classify each patient's normal cardiac behavior through the Hash function. The performance of R wave detection and abnormal beat classification is evaluated by using MIT-BIH arrhythmia database. The achieved scores indicate the average of 99.33% in R wave detection and the rate of 0.32% in abnormal beat classification error.

• Journal of Broadcast Engineering
• /
• v.16 no.6
• /
• pp.902-915
• /
• 2011

Recently in the area-based stereo matching field, Adaptive Support-Weight (ASW) method that weights matching cost adaptively according to the luminance intensity and the geometric difference shows promising matching performance. However, ASW requires more computational cost than other matching algorithms do and its real-time implementation becomes impractical. By applying Integral Histogram technique after approximating to the Bilateral filter equation, the computational time of ASW can be restricted in constant time regardless of the support window size. However, Integral Histogram technique causes loss of the matching accuracy during approximation process of the original ASW equation. In this paper, we propose a novel algorithm that maintains the ASW algorithm's matching accuracy while reducing the computational costs. In the proposed algorithm, we propose Sub-Block method that groups the pixels within the support area. We also propose the method adjusting the disparity search range depending on edge information. The proposed technique reduces the calculation time efficiently while improving the matching accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.2 s.40
• /
• pp.159-167
• /
• 2006

Lipreading has been suggested as one of the methods to improve the performance of speech recognition in noisy environment. However, existing methods are developed and implemented only in software. This paper suggests a hardware design for real-time lipreading. For real-time processing and feasible implementation, we decompose the lipreading system into three parts; image acquisition module, feature vector extraction module, and recognition module. Image acquisition module capture input image by using CMOS image sensor. The feature vector extraction module extracts feature vector from the input image by using parallel block matching algorithm. The parallel block matching algorithm is coded and simulated for FPGA circuit. Recognition module uses HMM based recognition algorithm. The recognition algorithm is coded and simulated by using DSP chip. The simulation results show that a real-time lipreading system can be implemented in hardware.

• The Journal of the Korea Contents Association
• /
• v.10 no.1
• /
• pp.19-26
• /
• 2010

This paper proposes a classifier based on rectangular feature to detect face in real time. The goal is to realize a strong detection algorithm which satisfies both efficiency in calculation and detection performance. The proposed algorithm consists of the following three stages: Feature creation, classifier study and real time facial domain detection. Feature creation organizes a feature set with the proposed five rectangular features and calculates the feature values efficiently by using SAT (Summed-Area Tables). Classifier learning creates classifiers hierarchically by using the AdaBoost algorithm. In addition, it gets excellent detection performance by applying important face patterns repeatedly at the next level. Real time facial domain detection finds facial domains rapidly and efficiently through the classifier based on the rectangular feature that was created. Also, the recognition rate was improved by using the domain which detected a face domain as the input image and by using PCA and KNN algorithms and a Class to Class rather than the existing Point to Point technique.

• Journal of Navigation and Port Research
• /
• v.31 no.6
• /
• pp.523-530
• /
• 2007

Crane systems are very important in industrial fields to carry heavy objects such that many investigations about control of the systems are actively conducted for enhancing its control performance. This paper presents an adaptive control approach using the model matching for a complex 3-DOF nonlinear crane system. First, the system model is linearized through feedback linearization method and then PD control is applied in the approximated model. This linear model is considered as nominal to derive corrective control law for a perturbed crane model using Lyapunov theory. This corrective control is primitively aimed to compensate real-time control deviation due to partially known perturbation. We additionally study stability analysis of the crane control system using Lyapunov perturbation theory. Evaluation of our control approach is numerically carried out through computer simulation and its superiority is demonstrated comparing with the classical control.

• Proceedings of the Korea Contents Association Conference
• /
• 2016.05a
• /
• pp.135-136
• /
• 2016

스마트 폰이 많이 보급되고 인터넷과 네트워크의 기술이 발달 하면서 많은 서비스 앱들이 개발되고 있다. 현재 스마트 폰은 컴퓨터를 대체할 정도의 수준으로 발전하고 있으며 기존의 컴퓨터로만 수행할 수 있는 서비스들도 스마트 폰을 통해 제공할 수 있도록 확장되고 있다. 본 논문에서는 위치기반의 스마트 택시 매칭 서비스 및 시스템 기법을 제안한다. 특히, 기사용 앱과 고객용 앱을 설계하고 스마트 폰이 보유한 고유 MAC 주소를 Key로 활용하고 사용자의 실시간 위치 좌표를 이용하여 고객과 기사의 매칭이 이루어지는 콜택시 서비스 시스템 구축 방법을 제안한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.180-183
• /
• 2010

본 연구에서는 개선된 영역기반의 패턴매칭 기법을 사용하여 이동물체의 탐색과 검출을 수행하였다. 시간에 따라 변화하는 이동물체의 안정된 추적을 위해 매 영상 프레임마다 이동물체의 윤곽선을 탐지하여 다음 영상에서의 템플릿으로 사용하기 위해 갱신하였으며, 패턴매칭의 연산속도 향상을 위해 패턴 정합률에 따라 영상을 다른 비율로 압축하여 추적하는 방법을 제안하였다. 기존의 영상파일을 사용하여 시뮬레이션 한 결과 이동물체의 검출과 추적에 양호한 동작을 보여주었으며 제안된 방법의 실시간 동작 가능성을 조사하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.164-165
• /
• 2018

2017년 3월에 NVIDIA에서 출시한 Jetson TX2는 GPU를 탑재한 고성능의 임베디드 보드이다. 이 제품은 GPU를 이용한 병렬 처리를 통해 임베디드 시스템 상에서 연산량이 많은 알고리즘을 동작시킬 수 있다. 스테레오 매칭 기법은 스테레오 카메라를 이용하여 깊이 정보를 획득할 수 있으며, 획득한 깊이 정보는 다양한 어플리케이션의 메타 데이터로써 활용될 수 있다. 하지만 알고리즘의 연산량이 매우 많아 GPU를 탑재한 데스크톱에서만 동작하는 것이 일반적이었다. 이에 본 논문은 임베디드 보드인 Jetson TX2에서 기존에 개발되었던 스테레오 매칭 알고리즘들을 동작시키고 성능 분석을 통해 실시간 동작 여부에 대한 연구를 진행하였다.