• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.4
• /
• pp.851-859
• /
• 2011

In this paper, we propose the method that automatically extracts the silhouette and the joints of consecutive input image, and track joints to trace object for interaction between human and computer. Also the proposed method presents the action of human being to map human body using joints. To implement the algorithm, we model human body using 14 joints to refer to body size. The proposed method converts RGB color image acquired through a single camera to hue, saturation, value images and extracts body's silhouette using the difference between the background and input. Then we automatically extracts joints using the corner points of the extracted silhouette and the data of body's model. The motion of object is tracted by applying block-matching method to areas around joints among all image and the human's motion is mapped using positions of joints. The proposed method is applied to the test videos and the result shows that the proposed method automatically extracts joints and effectively maps human body by the detected joints. Also the human's action is aptly expressed to reflect locations of the joints

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.2
• /
• pp.71-75
• /
• 2013

Recently proliferating heterogeneous multimedia service environments should be able to deal with many different transmission speeds, image sizes, or qualities of video. However, not many existing video compression standards satisfy those necessities. To satisfy the functional requirements, the standardization of the H.264/AVC Scalable Extension (SE) technique has been recently completed. It is an extension of the H.264/AVC which can encode several image sizes and qualities at the same time as a single bitstream. To perform optimum mode decision, motion estimation is performed for all MB modes, and the RD costs are compared to identify an MB mode with the smallest RD cost. This increases computational complexity of H.264/AVC SE encoding. In this paper, we propose an early skip mode detection scheme to reduce candidate modes and suggest an algorithm of fast mode decision utilizing reference modes according to the mode history.

• Journal of Pharmacopuncture
• /
• v.13 no.3
• /
• pp.63-71
• /
• 2010

Objectives: Gallic acid (GA) is the major component of tannin which could be easily founded in various natural materials such as green tea, red tea, grape juice, and Corni Fructus. The purpose of this study is to investigate the effect of Gallic acid (GA) on production of interleukin (IL) in mouse macrophage Raw 264.7 cells stimulated by lipopolysaccharide (LPS). Methods: Productions of interleukins were measured by High-throughput Multiplex Bead based Assay with Bio-plex Suspension Array System based on $xMAP^{(R)}$ (multi-analyte profiling beads) technology. Firstly, cell culture supernatant was obtained after treatment with LPS and GA for 24 hour. Then, it was incubated with the antibody-conjugated beads for 30 minutes. And detection antibody was added and incubated for 30 minutes. And Strepavidin-conjugated Phycoerythrin (SAPE) was added. After incubation for 30 minutes, the level of SAPE fluorescence was analyzed on Bio-plex Suspension Array System and concentration of interleukin was determined. Results: The results of the experiment are as follows. 1. GA significantly inhibited the production of IL-3, IL-10, IL-12p40, and IL-17 in LPS-induced mouse macrophage RAW 264.7 cells at the concentration of 25, 50, 100, 200 uM (p<0.05). 2. GA significantly inhibited the production of IL-6 in LPS-induced mouse macrophage RAW 264.7 cells at the concentration of 50, 100, 200 uM (p<0.05). 3. GA diminished the production of some cytokine such as IL-4, IL-5, and IL-13 in LPS-induced mouse macrophage RAW 264.7 cells. 4. GA did not show the inhibitory effect on the production of IL-$1{\alpha}$ and IL-9 in LPS-induced mouse macrophage RAW 264.7 cells. Conclusions: These results suggest that GA has anti-inflammatory activity related with its inhibitory effects on the production of interleukins such as IL-3, IL-10, IL-12p40, IL-17, and IL-6 in LPS-induced macrophages.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.3
• /
• pp.1302-1309
• /
• 2012

In this paper, we propose applying differential techniques for 2D/3D video conversion to the objects grouped by depth information. One of the problems converting 2D images to 3D images using the technique tracking the motion of pixels is that objects not moving between adjacent frames do not give any depth information. This problem can be solved by applying relative height cue only to the objects which have no moving information between frames, after the process of splitting the background and objects and extracting depth information using motion vectors between objects. Using this technique all the background and object can have their own depth information. This proposed method is used to generate depth map to generate 3D images using DIBR(Depth Image Based Rendering) and verified that the objects which have no movement between frames also had depth information.

• Asian-Australasian Journal of Animal Sciences
• /
• v.20 no.5
• /
• pp.669-676
• /
• 2007

This study was conducted to detect quantitative trait loci (QTL) affecting growth and body composition in an $F_2$ reference population of Korean native pig and Landrace crossbreds. The three-generation mapping population was generated with 411 progeny from 38 $F_2$ full-sib families, and 133 genetic markers were used to produce a sex-average map of the 18 autosomes. The data set was analyzed using least squares Mendelian and parent-of-origin interval-mapping models. Lack-of-fit tests between the models were used to characterize QTL for mode of expressions. A total of 8 (39) QTL were detected at the 5% genome (chromosome)-wise level for the 17 analyzed traits. Of the 47 QTL detected, 21 QTL were classified as Mendelian expressed, 13 QTL as paternally expressed, 6 QTL as maternally expressed, and 7 QTL as partially expressed. Of the detected QTL at 5% genome-wise level, two QTL had Mendelian mode of inheritance on SSC6 and SSC9 for backfat thickness and bone weight, respectively, two QTL were maternally expressed for leather weight and front leg weight on SSC6 and SSC12, respectively, one QTL was paternally expressed for birth weight on SSC4, and three QTL were partially expressed for hot carcass weight and rear leg weight on SSC6, and bone weight on SSC13. Many of the Mendelian QTL had a dominant (complete or overdominant) mode of gene action, and only a few of the QTL were primarily additive, which reflects that heterosis for growth is appreciable in a cross between Korean native pig and Landrace. Our results indicate that alternate breed alleles of growth and body composition QTL are segregating between the two breeds, which could be utilized for genetic improvement of growth via marker-assisted selection.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.4
• /
• pp.739-746
• /
• 2016

The real-time railway safety monitoring and control system is for prevention of safety accidents, and this system adopts DDS (Data Distribution Service) standard based data transmission method to support integrated management of data from existing on-site safety detection devices. In this paper, we introduce the design of DDS-based data specification from on-site signal equipment on the conventional railway. For this, we (1) design UML data model of KRS SG 0062 standard which defines existing data specification, (2) define DDS Topics for DDS transmission and map KRS model to DDS Topic model, (3) suggest data transformation rules and (4) design network control QoS polices. In addition, we analysis actual on-site log data and validate our data specification design. DDS-based data transmission enables data compatibility among on-site devices and the real-time railway safety monitoring and control system, and allows efficient network management for a large amount of data transfer.

• Journal of Korea Multimedia Society
• /
• v.14 no.11
• /
• pp.1450-1457
• /
• 2011

Currently most of leak detection monitoring systems use digital maps with paying royalties, and this increases the cost of system construction and financial burdens on local self-governing bodies that manage such systems. Moreover, they have inefficiencies in repair and maintenance, functional expansion, and compatibility with other systems. Thus, this study developed a waterworks pipe network monitoring system that pursues low cost and high efficiency using general-purpose maps on the Internet such as google maps. As this system uses highly compatible free maps, it costs less in construction and its hardware requirements are lower than existing systems, and consequently, overall monitoring performance is enhanced and the cost of construction goes down sharply. This study also proposed a method for pipeline DB construction, which can be started together with the construction of the monitoring system, in order to improve the field applicability of the system.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.8
• /
• pp.868-874
• /
• 2014

This paper proposes a novel mapping algorithm in Omni-directional Vision SLAM based on an obstacle's feature extraction using Lucas-Kanade Optical Flow motion detection and images obtained through fish-eye lenses mounted on robots. Omni-directional image sensors have distortion problems because they use a fish-eye lens or mirror, but it is possible in real time image processing for mobile robots because it measured all information around the robot at one time. In previous Omni-Directional Vision SLAM research, feature points in corrected fisheye images were used but the proposed algorithm corrected only the feature point of the obstacle. We obtained faster processing than previous systems through this process. The core of the proposed algorithm may be summarized as follows: First, we capture instantaneous $360^{\circ}$ panoramic images around a robot through fish-eye lenses which are mounted in the bottom direction. Second, we remove the feature points of the floor surface using a histogram filter, and label the candidates of the obstacle extracted. Third, we estimate the location of obstacles based on motion vectors using LKOF. Finally, it estimates the robot position using an Extended Kalman Filter based on the obstacle position obtained by LKOF and creates a map. We will confirm the reliability of the mapping algorithm using motion estimation based on fisheye images through the comparison between maps obtained using the proposed algorithm and real maps.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.9
• /
• pp.1545-1550
• /
• 2006

In this paper, we propose a method for applying the CLEAN algorithm to an minimum variance distortionless response(MVDR) to estimate the location of multiple targets distributed in the ocean. The CLEAN algorithm is easy to implement in a linear processor, yet not in a nonlinear processor. In the proposed method, the CSDM of a Dirty map is separated into the CSDM of a Clean beam and the CSDM of the Residual, then an individual ambiguity surface(AMS) is generated. As such, the CLEAN algorithm can be applied to an MVDR, a nonlinear processor. To solve the ill-conditioned problem related to the matrix inversiion by an MVDR when using the CLEAN algorithm, Singular value decomposition(SVD) is carried out, then the reciprocal of small eigenvalues is replaced with zero. Experimental results show that the proposed method improves the performance of an MVDR.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.227-233
• /
• 2019

Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.