• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.1
• /
• pp.90-95
• /
• 2010

This paper describes the development of integrated head and eye tracker system. Vision based head tracker is performed and it has 7mm error in 300mm translation. The epi-polar method and point matching are used for determining a position of head and rotational degree. High brightness LEDs are installed on helmet and the installed pattern is very important to match the points of stereo system. Eye tracker also uses LED for constant illumination. A Position of gazed object(3m distance) is determined by pupil tracking and eye tracker has 1~5 pixel error. Integration of result data of each tracking system is important. RS-232C communication is applied to integrated system and triggering signal is used for synchronization.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.808-810
• /
• 2018

Pedestrian tracking is a particular problem of object tracking, and an important component in various vision-based applications, such as autonomous cars or surveillance systems. After several years of development, pedestrian tracking in videos is still a challenging problem because of various visual properties of objects and surrounding environment. In this research, we propose a tracking-by-detection system for pedestrian tracking, which incorporates Convolutional Neural Network (CNN) and color information. Pedestrians in video frames are localized by a CNN, then detected pedestrians are assigned to their corresponding tracklets based on similarities in color distributions. The experimental results show that our system was able to overcome various difficulties to produce highly accurate tracking results.

• Journal of KIISE
• /
• v.43 no.5
• /
• pp.606-612
• /
• 2016

The multi-view video service based on the DASH(Dynamic Adaptive Streaming over HTTP) switches the viewpoint or object which is selected by the user among the multiple video streams captured by multiple cameras. However, the problem is that the conventional DASH-based multi-view video service takes a long time to switch the viewpoint. The reason is that the conventional scheme switches to the new video stream after consuming all buffered segments of the previous video stream. In this paper, we propose a video streaming scheme for minimizing the viewpoint switching delay in the DASH-based multi-view video service. In order to minimize the viewpoint switching delay, the proposed scheme configures the video streams by controlling the GoP (Group of Pictures) size and controls the client buffer based on bandwidth estimation and playback buffer occupancy. Through the experimental results, we prove that the proposed scheme reduces the viewpoint switching delay.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.4
• /
• pp.186-193
• /
• 2005

The Terrestrial Digital Multimedia Broadcasting (T-DMB) system supplies high quality audio comparable with VCD in 7 inch display and high quality audio comparable CD at the mobile reception environment T-DMB will launch commercial service at the middle of 2005. However the bandwidth for audio data and the number of channels are restricted to 128 kbps and 2 respectively in the current T-DMB standard because of the limitation of available bandwidth for multimedia data. This Paper Proposes a novel media processor structure for providing multi-channel audio contents oyer T-DMB system allowing backward compatibility with the legacy T-DMB receiver. Furthermore. we also Propose an adaptive receiver structure to supply optimal audio contents on various speaker configuration in T-DMB receiver. To provide multi-channel audio contents allowing backward comaptilbity with the legacy T-DMB receiver, the additional data for multi-channel audio are defined as a dependent stream of main audio stream. The OD strucure for control an additional multi-channel audio elementary stream is proposed without changing the BIFS of the legacy T-DMB system.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.2
• /
• pp.261-271
• /
• 2009

Due to the recent rise of a need for 3 dimensional geospatial information on urban areas, general interest in aerial multi-view cameras has been on an increase. The conventional geospatial information system depends solely upon vertical images, while the multi-view camera is capable of taking both vertical and oblique images taken from multiple directions, thus making it easier for the user to interpret the object. Through our research we developed a prototype of a multi-view camera system that includes a camera system, GPS/INS, a flight management system, and a control system. We also studied and experimented with the camera viewing angles, the synchronization of image capture, the exposure delay, the data storage that must be considered for the development of the multi-view camera system.

• 전자공학회논문지 IE
• /
• v.45 no.4
• /
• pp.11-18
• /
• 2008

This study is implementation of attitude control system(ACS - Attitude Control System). for a multi legs robot. This study designs H/W of Inertial Measurement Unit (IMU) and attitude control algorithm S/W. Compare performance with Mtx and MTx in order to verify action performance of this system after implementation, and will verify a system integrated IMU of a multi-legs robot. ACS uses Gyro and an accelerometer and an earth magnetism sensor, and it is a system controlling a roll, pitch angle attitude of an object. Generally, low price MEMS is difficult to calculate a correct situation of an object as an error occurs severely the Inertial sensor. This study implements IMU in order to develop ACS as use MEMS, accelerometer, Gyro sensor and earth magnetism sensor. Design algorithm each a roll, pitch, yaw attitude guaranteeing regular performance, and do poling in a system as include an attitude calculation program in an IMU system implemented. Mixed output of Gyro and an accelerometer, and recompensed a roll, pitch angle, and loaded in this study on a target platform in order to implement the ACS which guaranteed performance more than a continuously regular level, and operated by real time, and did porting, and verified.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.57-64
• /
• 2023

The ROK military faces a significant challenge in its vigilance mission due to demographic problems, particularly the current aging population and population cliff. This study demonstrates the crucial role of the 4th industrial revolution and its core artificial intelligence algorithm in maximizing work efficiency within the Command&Control room by mechanizing simple tasks. To achieve a fully developed military surveillance system, we have chosen multi-object tracking (MOT) technology as an essential artificial intelligence component, aligning with our goal of an intelligent and automated surveillance system. Additionally, we have prioritized data visualization and user interface to ensure system accessibility and efficiency. These complementary elements come together to form a cohesive software application. The CCTV video data for this study was collected from the CCTV cameras installed at the 1st and 2nd main gates of the 00 unit, with the cooperation by Command&Control room. Experimental results indicate that an intelligent and automated surveillance system enables the delivery of more information to the operators in the room. However, it is important to acknowledge the limitations of the developed software system in this study. By highlighting these limitations, we can present the future direction for the development of military surveillance systems.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.135-143
• /
• 2015

A Multiplayer Online Game(MOG) is a game capable of supporting hundreds or thousands of players and is mostly played using the Internet. P2P(peer-to-peer) architectures for MOGs can potentially achieve high scalability, low cost, and good performance. The basic idea of many P2P-based games is to distribute the game state among peers and along with it processing, network, and storage tasks. In a primary-copy based replication scheme where any update to the object has to be first performed on the primary copy, this means distributing primary copies of objects among peers. Most multiplayer games use a primary-copy model in order to provide strong consistency control over an object. Games consist of various types of actions that have different levels of sensitivity and can be categorized according to their consistency requirements. With the appropriate consistency level of each action type within a game, this paper allows developers to choose the right trade-off between performance and consistency. The performance for P2P game architecture with the primary-copy model is evaluated through simulation experiments and analysis.

• Journal of the Korean Society of Mechanical Technology
• /
• v.13 no.2
• /
• pp.63-70
• /
• 2011

In the present study, we developed optimal heat supply algorithm which minimizes the heat loss through the distribution pipe line in group energy apartment. Heating load variation of group energy apartment building in accordance with outdoor air temperature was predicted by the correlation obtained from calorimeter measurements of whole households of apartment building. Supply water temperature and mass flow rate were conjugately controlled to minimize the heat loss rate through distribution pipe line. Group heating apartment located in Hwaseong city, Korea, which has 1,473 households divided in 4 regions, was selected as the object apartment for verifying the present heat supply control algorithm. Compared to the original heat supply system, 10.4% heat loss rate reduction can be accomplished by employing the present control algorithm.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.6
• /
• pp.2468-2478
• /
• 2018

We propose the Sparse Feature Convolutional Neural Network (SFCNN) to reduce the volume of convolutional neural networks (CNNs). Despite the superior classification performance of CNNs, their enormous network volume requires high computational cost and long processing time, making real-time applications such as online-training difficult. We propose an advanced network that reduces the volume of conventional CNNs by producing a region-based sparse feature map. To produce the sparse feature map, two complementary region-based value extraction methods, cluster max extraction and local value extraction, are proposed. Cluster max is selected as the main function based on experimental results. To evaluate SFCNN, we conduct an experiment with two conventional CNNs. The network trains 59 times faster and tests 81 times faster than the VGG network, with a 1.2% loss of accuracy in multi-class classification using the Caltech101 dataset. In vehicle classification using the GTI Vehicle Image Database, the network trains 88 times faster and tests 94 times faster than the conventional CNNs, with a 0.1% loss of accuracy.