Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
Journal of Korea Multimedia Society
Journal Basic Information
Journal DOI :
Korea Multimedia Society
Editor in Chief :
Volume & Issues
Volume 15, Issue 12 - Dec 2012
Volume 15, Issue 11 - Nov 2012
Volume 15, Issue 10 - Oct 2012
Volume 15, Issue 9 - Sep 2012
Volume 15, Issue 8 - Aug 2012
Volume 15, Issue 7 - Jul 2012
Volume 15, Issue 6 - Jun 2012
Volume 15, Issue 5 - May 2012
Volume 15, Issue 4 - Apr 2012
Volume 15, Issue 3 - Mar 2012
Volume 15, Issue 2 - Feb 2012
Volume 15, Issue 1 - Jan 2012
Selecting the target year
Dynamic Human Activity Recognition Based on Improved FNN Model
Xu, Wenkai ; Lee, Eung-Joo ;
Journal of Korea Multimedia Society, volume 15, issue 4, 2012, Pages 417~424
DOI : 10.9717/kmms.2012.15.4.417
In this paper, we propose an automatic system that recognizes dynamic human gestures activity, including Arabic numbers from 0 to 9. We assume the gesture trajectory is almost in a plane that called principal gesture plane, then the Least Squares Method is used to estimate the plane and project the 3-D trajectory model onto the principal. An improved FNN model combined with HMM is proposed for dynamic gesture recognition, which combines ability of HMM model for temporal data modeling with that of fuzzy neural network. The proposed algorithm shows that satisfactory performance and high recognition rate.
Interaction Augmented Reality System using a Hand Motion
Choi, Kwang-Woon ; Jung, Da-Un ; Lee, Suk-Han ; Choi, Jong-Soo ;
Journal of Korea Multimedia Society, volume 15, issue 4, 2012, Pages 425~438
DOI : 10.9717/kmms.2012.15.4.425
In this paper, We propose Augmented Reality (AR) System for the interaction between user's hand motion and virtual object motion based on computer vision. The previous AR system provides inconvenience to user because the users have to control the marker and the sensor like a tracker. We solved the problem through hand motion and provide the convenience to the user. Also the motion of virtual object using a physical phenomenon gives a reality. The proposed system obtains geometrical information by the marker and hand. The system environments like virtual space of moving virtual ball and bricks are made by using the geometrical information and user's hand motion is obtained from the hand's information with extracted feature point through the taping hand. And it registers a virtual plane stably by getting movement of the feature points. The movement of the virtual ball basically is parabolic motion with a parabolic equation. When the collision occurs either the planes or the bricks, we show movement of the virtual ball with ball position and normal vector of plane and the ball position is faulted. So we showed corrected ball position through experiment. and we proved that this system can replaced the marker system to compare to jitter of augmented virtual object and progress speed with it.
TFT-LCD Defect Detection Using Mean Difference Between Local Regions Based on Multi-scale Image Reconstruction
Jung, Chang-Do ; Lee, Seung-Min ; Yun, Byoung-Ju ; Lee, Joon-Jae ; Choi, Il ; Park, Kil-Houm ;
Journal of Korea Multimedia Society, volume 15, issue 4, 2012, Pages 439~448
DOI : 10.9717/kmms.2012.15.4.439
TFT-LCD panel images have non-uniform brightness, noise signal and defect signal. It is hard to divide defect signal because of non-uniform brightness and noise signal, so various divide methods have being developed. In this paper, we suggest method to divide defective regions on TFT-LCD panel image by estimating a menas of two different size of windows, which is suggested by Eikvil et al., and using difference of them. But in this method, the size of detectable defects is restricted by the size of window, hence it has inefficient problem that the size of window have to increase to divide a large defect region. To solve this problem we suggest an algorithm which can divide various size of defects, by using Multi-scale and restrict a detectable size of defects in each scale. To prove an efficiency of suggested algorithm, we show that resulting images of real TFT-LCD panel images and an artificial image with various defects.
Tracking and Face Recognition of Multiple People Based on GMM, LKT and PCA
Lee, Won-Oh ; Park, Young-Ho ; Lee, Eui-Chul ; Lee, Hee-Kyung ; Park, Kang-Ryoung ;
Journal of Korea Multimedia Society, volume 15, issue 4, 2012, Pages 449~471
DOI : 10.9717/kmms.2012.15.4.449
In intelligent surveillance systems, it is required to robustly track multiple people. Most of the previous studies adopted a Gaussian mixture model (GMM) for discriminating the object from the background. However, it has a weakness that its performance is affected by illumination variations and shadow regions can be merged with the object. And when two foreground objects overlap, the GMM method cannot correctly discriminate the occluded regions. To overcome these problems, we propose a new method of tracking and identifying multiple people. The proposed research is novel in the following three ways compared to previous research: First, the illuminative variations and shadow regions are reduced by an illumination normalization based on the median and inverse filtering of the L*a*b* image. Second, the multiple occluded and overlapped people are tracked by combining the GMM in the still image and the Lucas-Kanade-Tomasi (LKT) method in successive images. Third, with the proposed human tracking and the existing face detection & recognition methods, the tracked multiple people are successfully identified. The experimental results show that the proposed method could track and recognize multiple people with accuracy.
Brick Path Recognition Using Image Shape Pattern and Texture Feature
Woo, Byung-Seok ; Yang, Sung-Min ; Jo, Kang-Hyun ;
Journal of Korea Multimedia Society, volume 15, issue 4, 2012, Pages 472~484
DOI : 10.9717/kmms.2012.15.4.472
Raised or plain block is widely used for the pedestrian's safe passage. The insincere construction, insufficient maintenance and obstacle overlaid on the pavement cause pedestrian's accidents. This paper proposes a method to detect brick path by analyzing the shape pattern and texture feature of brick located in visible distance for a safe passage. A brick appears to a regular type because of its specific shape which repeats with its sized gap and its type varies according to the surrounding environment or use. This paper shows a method which extracts the shape pattern by analyzing single surface polygon and its frequency appearing in road area. The shape pattern is used to detect similar shape regions. Some regions are not detected because extraneous substances or chopped bricks distort the original shape. This problem can be solved by analyzing the texture feature vector. The analyzed vector of the previously detected regions yields the Gaussian distribution. This value in each undetected region is computed and checked whether it's satisfied with Gaussian distribution or not. The satisfied region is detected as the brick path. The experiment was performed with the various type's bricks to recognize so that the results showed as accurate as 95.9% in average.
Efficient Motion Information Representation in Splitting Region of HEVC
Lee, Dong-Shik ; Kim, Young-Mo ;
Journal of Korea Multimedia Society, volume 15, issue 4, 2012, Pages 485~491
DOI : 10.9717/kmms.2012.15.4.485
This paper proposes 'Coding Unit Tree' based on quadtree efficiently with motion vector to represent splitting information of a Coding Unit (CU) in HEVC. The new international video coding, High Efficiency Video Coding (HEVC), adopts various techniques and new unit concept: CU, Prediction Unit (PU), and Transform Unit (TU). The basic coding unit, CU is larger than macroblock of H.264/AVC and it splits to process image-based quadtree with a hierarchical structure. However, in case that there are complex motions in CU, the more signaling bits with motion information need to be transmitted. This structure provides a flexibility and a base for a optimization, but there are overhead about splitting information. This paper analyzes those signals and proposes a new algorithm which removes those redundancy. The proposed algorithm utilizes a type code, a dominant value, and residue values at a node in quadtree to remove the addition bits. Type code represents a structure of an image tree and the two values represent a node value. The results show that the proposed algorithm gains 13.6% bit-rate reduction over the HM-1.0.
Improved Contour Region Coding Method based on Scalable Depth Map for 3DVC
Kang, Jin-Mi ; Jeong, Hye-Jeong ; Chung, Ki-Dong ;
Journal of Korea Multimedia Society, volume 15, issue 4, 2012, Pages 492~500
DOI : 10.9717/kmms.2012.15.4.492
In this paper, improved contour region coding method is proposed to accomplish better depth map coding performance. First of all, in order to use correlation between color video and depth map, a structure in SVC is applied to 3DVC. This can reduce bit-rate of the depth map while supporting the video to be transferred via various collection of network. As the depth map is mainly used to synthesize videos from different views, corrupted contour region can damage the overall quality of video. We hereby adapt a new differential quantization method when separating the contour region. The experimental results show that the proposed method can improve video quality by 0.06~0.5dB which translate the bit rate saving by 0.1~1.15%, when compared to the reference software.
Human-Computer Natur al User Inter face Based on Hand Motion Detection and Tracking
Xu, Wenkai ; Lee, Eung-Joo ;
Journal of Korea Multimedia Society, volume 15, issue 4, 2012, Pages 501~507
DOI : 10.9717/kmms.2012.15.4.501
Human body motion is a non-verbal part for interaction or movement that can be used to involves real world and virtual world. In this paper, we explain a study on natural user interface (NUI) in human hand motion recognition using RGB color information and depth information by Kinect camera from Microsoft Corporation. To achieve the goal, hand tracking and gesture recognition have no major dependencies of the work environment, lighting or users' skin color, libraries of particular use for natural interaction and Kinect device, which serves to provide RGB images of the environment and the depth map of the scene were used. An improved Camshift tracking algorithm is used to tracking hand motion, the experimental results show out it has better performance than Camshift algorithm, and it has higher stability and accuracy as well.
Accurate Face Pose Estimation and Synthesis Using Linear Transform Among Face Models
Suvdaa, B. ; Ko, J. ;
Journal of Korea Multimedia Society, volume 15, issue 4, 2012, Pages 508~515
DOI : 10.9717/kmms.2012.15.4.508
This paper presents a method that estimates face pose for a given face image and synthesizes any posed face images using Active Appearance Model(AAM). The AAM that having been successfully applied to various applications is an example-based learning model and learns the variations of training examples. However, with a single model, it is difficult to handle large pose variations of face images. This paper proposes to build a model covering only a small range of angle for each pose. Then, with a proper model for a given face image, we can achieve accurate pose estimation and synthesis. In case of the model used for pose estimation was not trained with the angle to synthesize, we solve this problem by training the linear relationship between the models in advance. In the experiments on Yale B public face database, we present the accurate pose estimation and pose synthesis results. For our face database having large pose variations, we demonstrate successful frontal pose synthesis results.
Performance Evaluation of Distributed Cooperative MAC Protocol Algorithm for Enhancing Multimedia QoS of WiMedia Communication Network
Kim, Jin-Woo ; Lee, Yeon-Woo ; Lee, Seong-Ro ;
Journal of Korea Multimedia Society, volume 15, issue 4, 2012, Pages 516~525
DOI : 10.9717/kmms.2012.15.4.516
In this paper, an efficient technique for enhancing the QoS of multimedia service for an WiMedia network applying distributed cooperative medium access (D-MAC) protocol is proposed. D-MAC protocol has been proposed to support high-rate Wireless Personal Area Networks (HR-WPANs) by the WiMedia Alliance. Unlike the centralized IEEE 802.15.3 MAC, the D-MAC UWB specified by WiMedia supports all devices to be self-organized and removes the SOP (Simultaneous Operating Piconet) problem, i.e., packet collisions between overlapped piconets in the centralized IEEE 802.15.3 MAC. However the WiMedia D-MAC can't prevent reduce the throughput degradation occurred by mobile nodes with low data rate. Therefore, a distributed cooperative MAC protocol for multi-hop UWB network is proposed in this paper. The proposed technique can intelligently select the transmission path with higher data rate to provide real-time multimedia services with minimum delay, thus enhances QoS of multimedia service.
A New Information Data Hiding Scheme based on Pattern Information of Secret Data
Kim, Ki-Jong ; Shin, Sang-Ho ; Yoo, Kee-Young ;
Journal of Korea Multimedia Society, volume 15, issue 4, 2012, Pages 526~539
DOI : 10.9717/kmms.2012.15.4.526
This paper proposes a high capacity data hiding method using high frequence secret data indexing algorithm. Many novel data hiding methods based on LSB and PVD methods were presented to enlarge hiding capacity and provide an imperceptible quality. In this paper, first, calculating data iteration frequency of the secret message and make up the high frequency data index matrix (HFDT) using high frequence data's location information. Next, HFDT uses to that data hiding process on the cover image and recovering process on the stego image. The experimental results demonstrate the efficiency of the proposed high frequency secret data indexing method. For the data hiding method, experiments are conducted for four cases: 2 pattern secret data (2PD), 4 pattern secret data (4PD), 8 pattern secret data (8PD) and higher pattern secret data (HPD). When comparing the proposed method with other data hiding methods, for the HPD case, the results show that the proposed method has a good PSNR and more capacity, and for the other case, the results show that the proposed method has a higher PSNR and larger capacity.
A Design of Service Migration Mechanism in HTML5-based Convergence Service
Choi, Hun-Hoi ; Song, Eun-Ji ; Kim, Geun-Hyung ; Kim, Hwa-Sook ; Cho, Ki-Seong ;
Journal of Korea Multimedia Society, volume 15, issue 4, 2012, Pages 540~551
DOI : 10.9717/kmms.2012.15.4.540
Recently, the W3C has developed the HTML5 standard which gives the basis for providing various web applications on the web environments. Because of the advent of the smart devices and the broadband wireless network, users can accesse the web applications on the smart devices at anytime and anywhere. In addition, the demand on the multiscreen services, which enables users to use the appropriate device to their situation, has increased, since users have various smart devices. In this paper, we propose the grouping mechanism of web objects on the HTML5 based web platform, the extraction mechanism of the web object information which is used to create the web object on other devices, and the web object creation mechanism based on the received web object information. In addition, we propose the web service migration architecture between devices on the open web platform and implement the grouping, extraction and creation mechanism of the web objects on the test web document and generic web document with Chrome extension. Finally, we implement the delivery mechanism of the web object information between devices using the node.js and the WebSocket technologies.
Design and Implementation of a Web-based Simulator for Educating Page Replacement Algorithms
Koh, Jeong-Gook ;
Journal of Korea Multimedia Society, volume 15, issue 4, 2012, Pages 552~559
DOI : 10.9717/kmms.2012.15.4.552
Operating Systems is a discipline which handles complex and concepts related to its components and how an operating system works. However, most of the OS courses have been textbook-oriented theoretical classes. Therefore, many instructors have tried to make use of educational tools to help students understand a lecture and arouse their interests consistently. This paper describes the design and implementation of a web-based page replacement simulator which shows the process of page replacement algorithms visually. The academic achievement evaluation and t-test results for 2010's students and 2011's show that the differences of the correct answer ratios for the exam about page replacement algorithms and the scores between two groups are meaningful. And the results of survey show that a page replacement simulator is useful as an educational tool which causes the interests about operating systems and enhances the understanding of a lecture.
A Study On The Development Of Virtual Underwater Environment And Sensory Simulator
Youn, Jae-Hong ; Hur, Gi-Taek ; Kang, Im-Chul ;
Journal of Korea Multimedia Society, volume 15, issue 4, 2012, Pages 560~568
DOI : 10.9717/kmms.2012.15.4.560
As for the implementation technology of virtual space, the experience method becomes multifunctional and it recognizes movement, sound, temperature and pressure and is expanding to the studies on the interaction possible intelligent interaction technology field between contents and users. The virtual reality technology is being studied to apply the 3D graphic technology and physical phenomena to virtual space to increase the sense of reality and use hardware devices to the virtual environment to increase immersive experience. The production of interactive contents about the virtual underwater environment needs bidirectional interface technology to connect hardware devices and ocean contents in order to increase the sense of a user to increase the sense of immersion. In this study, it tried to express the virtual underwater environment with the sense of actuality and reality from the analysis of the environmental factors according to changes in depth of water and from the application of the normalized underwater physical laws. Also it was to develop sensory contents having to experience the skin scuba without directly entering the water by connecting a sensory simulator about the skin scuba with the virtual underwater environment.