• Journal of Korea Multimedia Society
• /
• v.7 no.11
• /
• pp.1597-1609
• /
• 2004

A lot of lipreading system has been proposed to compensate the rate of speech recognition dropped in a noisy environment. Previous lipreading systems work on some specific conditions such as artificial lighting and predefined background color. In this paper, we propose a real-time lipreading system which allows the motion of a speaker and relaxes the restriction on the condition for color and lighting. The proposed system extracts face and lip region from input video sequence captured with a common PC camera and essential visual information in real-time. It recognizes utterance words by using the visual information in real-time. It uses the hue histogram model to extract face and lip region. It uses mean shift algorithm to track the face of a moving speaker. It uses PCA(Principal Component Analysis) to extract the visual information for learning and testing. Also, it uses HMM(Hidden Markov Model) as a recognition algorithm. The experimental results show that our system could get the recognition rate of 90% in case of speaker dependent lipreading and increase the rate of speech recognition up to 40～85% according to the noise level when it is combined with audio speech recognition.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.5
• /
• pp.396-401
• /
• 2016

Owing to developments in the internet of things, many products have developed and various researches have processed. Smart home systems in Internet of things area are receiving attention from many people than the other areas. Autonomous mobile robots perform various parts in many industries. In this paper, a smart housekeeping robot was implemented using internet of things and an autonomous mobile robot. In order to make a smart housekeeping robot, Raspberry Pi, wireless USB camera, and uBrain robot of Huins Corp. is used. To control the robot, cell-phone connected with IP of Raspberry Pi, and then Raspberry Pi connected with uBrain robot using Bluetooth. a smart housekeeping robot was controlled using commands of a cell-phone application. If some user wants to move a robot automatically, we implemented that a robot can be chosen an autonomous driving mode from the user. In addition, we checked a realtime video using a cell-phone and computer. This smart housekeeping robot can help user check their own homes in real time.

• Korean Chemical Engineering Research
• /
• v.49 no.1
• /
• pp.41-46
• /
• 2011

We investigated experimentally the properties of dust explosion through lycopodium particle clouds in a duct to provide the fundamental knowledge. Propagating dust flames in the vertical duct of 120 cm height and 12 cm square cross-section were observed by digital video camera and flame front is visualized using by PIV(Particle Image Velocimetry) system. As the result, when the same average dust concentration existed in the vertical duct, downward flame propagation was faster than the upward flame propagation, its rate increased with dust concentration in 300g/$m^3$. Post flames were caused by the ignition of unburned particles which flowed into the rear region of flame from passage between flame and duct wall, and they generated regardless of duct condition. Also, it was found that appearance frequency of post flames during dust flame propagations increased with the increase of dust concentration.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.11B
• /
• pp.1303-1310
• /
• 2009

Glassless 3D display requires multiple images taken from different viewpoints to show a scene. The simplest way to get multi-view image is using multiple camera that as number of views are requires. To do that, synchronize between cameras or compute and transmit lots of data comes critical problem. Thus, generating such a large number of viewpoint images effectively is emerging as a key technique in 3D video technology. Image-based view synthesis is an algorithm for generating various virtual viewpoint images using a limited number of views and depth maps. In this paper, because the virtual view image can be express as a transformed image from real view with some depth condition, we propose an algorithm to compute multi-view synthesis from two reference view images and their own depth-map by stepwise duplex forward mapping. And also, because the geometrical relationship between real view and virtual view is repetitively, we apply our algorithm into OpenGL Shading Language which is a programmable Graphic Process Unit that allow parallel processing to improve computation time. We demonstrate the effectiveness of our algorithm for fast view synthesis through a variety of experiments with real data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.12
• /
• pp.546-554
• /
• 2019

Typically, closed-circuit television (CCTV) monitoring is mainly used for post-processes (i.e. to provide evidence after an incident has occurred), but by using a streaming video feed, machine-based learning, and advanced image recognition techniques, current technology can be extended to respond to crimes or reports of missing persons in real time. The multi-CCTV cooperation technique developed in this study is a program model that delivers similarity information about a suspect (or moving object) extracted via CCTV at one location and sent to a monitoring agent to track the selected suspect or object when he, she, or it moves out of range to another CCTV camera. To improve the operating efficiency of local government CCTV control centers, we describe here the partial automation of a CCTV control system that currently relies upon monitoring by human agents. We envisage an integrated crime prevention service, which incorporates the cooperative CCTV network suggested in this study and that can easily be experienced by citizens in ways such as determining a precise individual location in real time and providing a crime prevention service linked to smartphones and/or crime prevention/safety information.

• Cartoon and Animation Studies
• /
• s.48
• /
• pp.117-139
• /
• 2017

The possibility of interactivity of digital media environment is adopted in human expression system and integrates the dynamic aspect of digital technology with expressive structure, thereby transforming the paradigm of image acceptance as well as image expression range. Virtual reality images have an important meaning in that they are changing the one-way mechanism of production and acceptance of images that lead to producers-video-audiences beyond the problem of verisimilitude such as how vividly they simulate reality. First of all, the virtual reality image is not one-sided but interactive image composed by the user. Viewing a virtual reality image does not just see the camera shine, but it gets the same view as in the real world. Therefore, the image that was controlled through framing changes to be configured positively by the user. This implies a change in the paradigm of image acceptance as well as a change in the existing form of the image itself. In addition, the narrative structure of the image and the subjects that are formed in the process are also required to be discussed. In the virtual reality image, the user 's gaze is a fusion of the gaze inside the image and the gaze outside the image. This is because the position of the user as the subject of the gaze in the virtual reality image is continuously restricted by the device of the discourse such as the editing and the narration of the shot. The significance of the virtual reality image is not aesthetically perfect but it is reconstructed according to the user to reflect the existence of the user positively and engage the user in the image.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.10C
• /
• pp.933-941
• /
• 2006

In this paper, we proposed an efficient coding method for digital hologram (fringe pattern) acquired by a CCD camera or by computer generation using multi-view prediction technique and MPEG video compression standard technique. It proceeds each R, G, or B color component separately. The basic processing unit is a partial image segmented into the size of $N{\times}N$. Each partial image retains the information of the whole object. This method generates an assembled image for a row of the segmented and frequency-transformed partial images, which is the basis of the coding process. That is, a motion estimation and compensation technique of MPEG is applif:d to the reconstructed images from the assembled images with the disparities found during generation of assembled image and the original partial images. Therefore the compressed results are the disparity of eachpartial image to form the assembled image for the corresponding row, assembled image, and the motion vectors and the compensated image for each partial image. The experimental results with the implemented algorithm showed that the proposed method has NC (Normal Correlation) values about 4% higher than the previous method, by which ours has better compression efficiency. Consequently, the Proposed method is expected to be used effectively in the application areas to transmit the digital hologram data. can be identified in comparison with the previous researches and commercial IPs.

• Journal of Digital Convergence
• /
• v.14 no.2
• /
• pp.183-190
• /
• 2016

This paper proposes algorithm to reduce the computing time in a neural network that reduces transmission of data for tracking mobile objects in surveillance networks in terms of detection and communication load. Object Detection can be defined as follows : Given image sequence, which can forom a digitalized image, the goal of object detection is to determine whether or not there is any object in the image, and if present, returns its location, direction, size, and so on. But object in an given image is considerably difficult because location, size, light conditions, obstacle and so on change the overall appearance of objects, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact object detection which overcomes some restrictions by using neural network. Proposed system can be object detection irrelevant to obstacle, background and pose rapidly. And neural network calculation time is decreased by reducing input vector size of neural network. Principle Component Analysis can reduce the dimension of data. In the video input in real time from a CCTV was experimented and in case of color segment, the result shows different success rate depending on camera settings. Experimental results show proposed method attains 30% higher recognition performance than the conventional method.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.4
• /
• pp.87-98
• /
• 2011

Detecting a moving object from videos and tracking it are basic and necessary preprocessing steps in many video systems like object recognition, context aware, and intelligent visual surveillance. In this paper, we propose a method that is able to detect a moving object quickly and accurately in a condition that background and light change in a real time. Furthermore, our system detects strongly an object in a condition that the target object is covered with other objects. For effective detection, effective Eigen-space and FCM are combined and employed, and a CONDENSATION algorithm is used to trace a detected object strongly. First, training data collected from a background image are linear-transformed using Principal Component Analysis (PCA). Second, an Eigen-background is organized from selected principal components having excellent discrimination ability on an object and a background. Next, an object is detected with FCM that uses a convolution result of the Eigen-vector of previous steps and the input image. Finally, an object is tracked by using coordinates of an detected object as an input value of condensation algorithm. Images including various moving objects in a same time are collected and used as training data to realize our system that is able to be adapted to change of light and background in a fixed camera. The result of test shows that the proposed method detects an object strongly in a condition having a change of light and a background, and partial movement of an object.

• Journal of the Korean Society for Railway
• /
• v.20 no.2
• /
• pp.165-172
• /
• 2017

High frequency squeal noise can be generated when a railroad vehicle runs a sharp curved section; this noise causes environmental complaints and excessive wear on the wheel and the railroad track. In this paper, curved squeal noise experiments on a commercial railway were carried out to investigate this phenomenon. The relationship of the squeal noise pressure level, the frequency characteristics, the railway running speed, and the modal behavior of the wheel were investigated. At the same time, the lateral motion of the wheel relative to the rail was captured using a video camera; wheel movement was calculated when the noise was generated. queal noise occurred at the highest level at the inner front wheel; this phenomena is considered to be related to the lateral vibration response characteristics of the wheel. It can be seen that the magnitude of this squeal noise is not directly related to the increase in vehicle speed.