• Journal of Digital Contents Society
• /
• v.15 no.4
• /
• pp.449-455
• /
• 2014

Detection of moving objects is a fundamental task in most of the computer vision applications, such as video surveillance, activity recognition and human motion analysis. This is a difficult task due to many challenges in realistic scenarios which include irregular motion in background, illumination changes, objects cast shadows, changes in scene geometry and noise, etc. In this paper, we propose an foreground extraction algorithm based on codebook, a database of information about background pixel obtained from input image sequence. Initially, we suppose a first frame as a background image and calculate difference between next input image and it to detect moving objects. The resulting difference image may contain noises as well as pure moving objects. Second, we investigate a codebook with color and brightness of a foreground pixel in the difference image. If it is matched, it is decided as a fault detected pixel and deleted from foreground. Finally, a background image is updated to process next input frame iteratively. Some pixels are estimated by input image if they are detected as background pixels. The others are duplicated from the previous background image. We apply out algorithm to PETS2009 data and compare the results with those of GMM and standard codebook algorithms.

• The Journal of Korean Association of Computer Education
• /
• v.19 no.3
• /
• pp.21-34
• /
• 2016

This study aims to develop user experience based mathematical program for self-directed learning. To meet its aim this program is designed and developed according to the process and method of 'ADDIE', general design model of education program. The features of this program are as follows. First, teacher can set questions conveniently through intuitive system of web and learner can solve questions at anytime and anywhere through instant access to application. Second, learner can solve different types of questions based on powerful question database and teacher can provide instantaneous feedback on them. Third, learner's circulation learning can be possible by utilizing paper-video explanation and wrong answer note and teacher supports learner's active learning management though group achievement management.

• Journal of Korea Society of Industrial Information Systems
• /
• v.17 no.3
• /
• pp.35-42
• /
• 2012

The database for driving patterns can be utilized in various system such as automatic driving system, driver safety system, and it can be helpful to monitor driving style. Therefore, we propose a driving pattern recognition system in which the sensor streams from a smartphone are recorded and used for recognizing driving events. In this paper we focus on the driving pattern recognition that is an essential and preliminary step of driving style recognition. We divide input sensor streams into 7 driving patterns such as, Left-turn(L), U-turn(U), Right-turn(R), Rapid-Braking(RB), Quick-Start(QS), Rapid-Acceleration (RA), Speed-Bump(SB). To classify driving patterns, first, a preprocessing step for data smoothing is followed by an event detection step. Last the detected events are classified by DTW(Dynamic Time Warping) algorithm. For assisting drivers we provide the classified pattern with the corresponding video stream which is recorded with its sensor stream. The proposed system will play an essential role in the safety driving system or driving monitoring system.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.4
• /
• pp.682-691
• /
• 2017

In this paper, we propose the fusion design methodology of both pedestrian detection and object tracking system realized with the aid of HOG-PCA based RBFNN pattern classifier. The proposed system includes detection and tracking parts. In the detection part, HOG features are extracted from input images for pedestrian detection. Dimension reduction is also dealt with in order to improve detection performance as well as processing speed by using PCA which is known as a typical dimension reduction method. The reduced features can be used as the input of the FCM-based RBFNNs pattern classifier to carry out the pedestrian detection. FCM-based RBFNNs pattern classifier consists of condition, conclusion, and inference parts. FCM clustering algorithm is used as the activation function of hidden layer. In the conclusion part of network, polynomial functions such as constant, linear, quadratic and modified quadratic are regarded as connection weights and their coefficients of polynomial function are estimated by LSE-based learning. In the tracking part, object tracking algorithms such as mean shift(MS) and cam shift(CS) leads to trace one of the pedestrian candidates nominated in the detection part. Finally, INRIA person database is used in order to evaluate the performance of the pedestrian detection of the proposed system while MIT pedestrian video as well as indoor and outdoor videos obtained from IC&CI laboratory in Suwon University are exploited to evaluate the performance of tracking.

• Journal of The Korean Association of Information Education
• /
• v.7 no.2
• /
• pp.199-206
• /
• 2003

XML is becoming a new developing tool of web technology because of its ability of data management and flexibility in data presentation. So it's well researched that the reusability and integration with learning objects such as text, image, sound, video and plug-in programs of web contents in computer education. But the research for storing, extracting and integrating metadata about learning object was needed prior to implementing online learning system to integrate and manage it. Therefore this study propose a new method of using web service of DBMS for extracting learning object's metadata in database server which located in 3-tier system. To evaluate the efficiency of proposed method, The test server and two DBMSs(MS SQL Server 2000 and Oracle 9i) which have 30 metadata was implemented and the response time of it was measured. The response time of it was short, but in order to using this method the additional programming with SAX/DOM was necessary.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.7
• /
• pp.1213-1223
• /
• 1994

VSATs(Very Small Aperture Terminals) have introduced new concepts in satellite business communications and are typically used in a star network configuration to provide information directly to the user`s premise. The characteristics of this system are low earth station costs, easy in stallation, compact, and very high flexibility for a varierty of applications (Credit Checks, Electronic Mail, Video Conferencing, Reservation System, Database Inquires, Order Entry, etc.). So, the requests of VSAT service have considerably enlarged. The link design of a VSAT network using Korea Sat. is discussed in this paper. This paper is intended to collect in a convient way the principle formula and reference data necessary to make overall performance calcurations and to calcurate antenna size. HPA power size and link margin of earth stations for satellite communications systems. Generally, because the antenna size of the Hub station in the VSAT system is bigger than the Remote station, the method of power allocations of inbound and outbound carriers is utilized in this paper. The size of Hub station and Remote station are assumed to be 3.7m and 1.2m. respectively.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.5
• /
• pp.48-55
• /
• 2009

Prior research works in indoor-outdoor classification have been conducted based on a simple combination of low-level features. However, since there are many challenging problems due to the extreme variability of the scene contents, most methods proposed recently tend to combine the low-level features with high-level information such as the presence of trees and sky. To extract these regions from videos, we need to conduct additional tasks, which may yield the increasing number of feature dimensions or computational burden. Therefore, an efficient indoor-outdoor scene classification method is proposed in this paper. First, the video is divided into the five same-sized blocks. Then we define and use the edge and color orientation histogram (ECOH) descriptors to represent each sub-block efficiently. Finally, all ECOH values are simply concatenated to generated the feature vector. To justify the efficiency and robustness of the proposed method, a diverse database of over 1200 videos is evaluated. Moreover, we improve the classification performance by using different weight values determined through the learning process.

• Nutrition Research and Practice
• /
• v.2 no.2
• /
• pp.114-120
• /
• 2008

A diet habit, which is developed in childhood, lasts for a life time. In this sense, nutrition education and early exposure to healthy menus in childhood is important. Children these days have easy access to the internet. Thus, a web-based nutrition education program for children is an effective tool for nutrition education of children. This site provides the material of the nutrition education for children with characters which are personified nutrients. The 151 menus are stored in the site together with video script of the cooking process. The menus are classified by the criteria based on age, menu type and the ethnic origin of the menu. The site provides a search function. There are three kinds of search conditions which are key words, menu type and "between" expression of nutrients such as calorie and other nutrients. The site is developed with the operating system Windows 2003 Server, the web server ZEUS 5, development language JSP, and database management system Oracle 10 g.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.922-934
• /
• 2020

The talent trading platform is a platform that brokers transactions such as program coding, media content production (video, music, presentation materials, etc.), design, learning, and repair. Existing talent trading platforms provide a server-client model-based service, which incurs server operating costs and arbitration labor costs for transactions, which has a disadvantage that users bear high service fees. This paper proposes a method to reduce server and database operation costs by uploading transaction information to blocks through the system as a distributed app (dApp) based on the Ethereum platform. In addition, it proposes a method to lower transaction fees by reducing the labor cost of transaction arbitrators through smart contracts. Compare and analyze the cost processing procedure and transaction fee size of the blockchain-based talent trading platform and the existing talent trading platform.

• Journal of Chest Surgery
• /
• v.56 no.5
• /
• pp.336-345
• /
• 2023

Background: The objective of this study was to demonstrate the safety, efficacy, and feasibility of intraoperative monitoring of the recurrent laryngeal nerves during thoracoscopic and robotic 3-field esophagectomy. Methods: This retrospective analysis details our initial experience using intraoperative nerve monitoring (IONM) during minimally invasive 3-field esophagectomy. Data were obtained from a prospectively maintained database and electronic medical records. The study included all patients who underwent minimally invasive (video-assisted thoracic surgery/robotic) transthoracic esophagectomy with neck anastomosis. The patients were divided into those who underwent IONM during the study period and a historical cohort who underwent 3-field esophagectomy without IONM at the same institution. Appropriate statistical tests were used to compare the 2 groups. Results: Twenty-four patients underwent nerve monitoring during minimally invasive 3-field esophagectomy. Of these, 15 patients underwent thoraco-laparoscopic operation, while 9 received a robot-assisted procedure. In the immediate postoperative period, 8 of 24 patients (33.3%) experienced vocal cord paralysis. Relative to a historical cohort from the same institution, who were treated with surgery without nerve monitoring in the preceding 5 years, a 26% reduction was observed in the nerve paralysis rate (p=0.08). On follow-up, 6 of the 8 patients with vocal cord paralysis reported a return to normal vocal function. Additionally, patients who underwent IONM exhibited a higher nodal yield and a decreased frequency of tracheostomy and bronchoscopy. Conclusion: The use of IONM during minimally invasive 3-field esophagectomy is safe and feasible. This technique has the potential to decrease the incidence of recurrent nerve palsy and increase nodal yield.