• Journal of Advanced Navigation Technology
• /
• v.14 no.2
• /
• pp.272-277
• /
• 2010

AR(Augmented Reality) needs medium between real and virtual, world, and recognition techniques are necessary to track an object continuously. Optical tracking using marker is mainly used, but it takes time and is inconvenient to attach marker onto the target objects. Therefore, many researchers try to develop markerless tracking techniques nowaday. In this paper, we extract features and 3D position from 3D objects and suggest realtime tracking based on these features and positions, which do not use just coplanar features and 2D position. We extract features using SURF, get rotation matrix and translation vector of 3D object using POSIT with these features and track the object in real time. If the extracted features are nor enough and it fail to track the object, then new features are extracted and re-matched to recover the tracking. Also, we get rotation in matrix and translation vector of 3D object using POSIT and track the object in real time.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.1015-1020
• /
• 2003

Among the techniques to protect private information by adopting biometrics, speaker verification is expected to be widely used due to advantages in convenient usage and implementation cost. Speaker verification should achieve a high degree of the reliability in the verification score, the flexibility in speech text usage, and the efficiency in verification system complexity. Continuants have excellent speaker-discriminant power and the modest number of phonemes in the category, and multilayer perceptrons (MLPs) have superior recognition ability and fast operation speed. In consequence, the two provide viable ways for speaker verification system to obtain the above properties. This paper implements a system to which continuants and MLPs are applied, and evaluates the system using a Korean speech database. The results of the experiment prove that continuants and MLPs enable the system to acquire the three properties.

• Journal of IKEEE
• /
• v.24 no.3
• /
• pp.743-753
• /
• 2020

In this paper, we propose a set of robustness indicators for immersive 360-degree video. With the full-fledged service of mobile carriers' 5G networks, it is possible to use large-capacity, immersive 360-degree videos at high speed anytime, anywhere. Since it can be illegally distributed in web-hard and torrents through DRM dismantling and various video modifications, however, evaluation indicators that can objectively evaluate the filtering performance for copyright protection are required. In this paper, a robustness indicators is proposed that applies the existing 2D Video robustness indicators and considers the projection method and reproduction method, which are the characteristics of Immersive 360-degree Video. The performance evaluation experiment has been carried out for a sample filtering system and it is verified that an excellent recognition rate of 95% or more has been achieved in about 3 second execution time.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.10
• /
• pp.4632-4641
• /
• 2011

The detailed production traceability information is a fundamental element in successful introduction and revitalization of traceability system. In this paper, we propose a production traceability information gathering system which is based on handwritten data digitalization technology in agro-livestock products. By the proposed system, we can effectively gather the detailed production traceability information with digital pen and the management ledger of paper document type by only writing the ledger. The server of the system generates the same digital image as the ledger and converts the handwritten data into digital text to insert the data into the database. Because the system is superior to data gathering system based on PC, PDA and touch screen in mobility, usability, data input speed, suitability in agro-livestock environment, it is possible to effectively gather traceability information of high quality by users even if they have low information ability and insufficient time to input data. We expect that the handwritten data digitalization technology is used to gather document based information in stage of manufacturing, distribution and marketing. In addition, this technology is applied to implementing advanced traceability system with RFID/USN based systems.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.8A
• /
• pp.639-647
• /
• 2012

Vision-based on-road vehicle detection is one of the key techniques in automotive driver assistance systems. However, due to the huge within-class variability in vehicle appearance and environmental changes, it remains a challenging task to develop an accurate and reliable detection system. In general, a vehicle detection system consists of two steps. The candidate locations of vehicles are found in the Hypothesis Generation (HG) step, and the detected locations in the HG step are verified in the Hypothesis Verification (HV) step. Since the final decision is made in the HV step, the HV step is crucial for accurate detection. In this paper, we propose using a reduced multivariate polynomial pattern classifier (RM) for the HV step. Our experimental results show that the RM classifier outperforms the well-known Support Vector Machine (SVM) classifier, particularly in terms of the fast decision speed, which is suitable for real-time implementation.

• Survey Research
• /
• v.3 no.2
• /
• pp.91-122
• /
• 2002

The use of internet is expanding globally in a rapid way. The situation is similar in Korea. The growth of internet affects the various aspects of a social system. Such an impact is not an exception in the field of survey data-collection. The internet survey method has gained a recognition as an important survey approach in the U.S and Europe. A number of Korean research organizations have already started implementing the new survey method, too. The time is quite ripe for the internet survey in Korea. However, it is hard to find ever a good literature review on the subject. This study intends to review the results of the past studies about the question of what factors influence the response rate, speed, and quality. The influencing factors incorporated in this review include six elements: personalization, the survey sponsorship, incentives, the questionaire format, prenotification, and follow-ups. Regarding there sis factors, the results of the past studies relating to the internet survey response are reviewed in a systematic way.

• The Journal of the Korea Contents Association
• /
• v.19 no.11
• /
• pp.92-101
• /
• 2019

This study used the Q-method to derive the structure of subjective opinions and perceptions of university students about the behavior of food delivery agency service provided by staff not directly employed in restaurants. For this purpose, the Q factor analysis was performed using the PC QUANL program for the Q-sort, which consists of a statement card, a P-sample, and a classification process. The results were classified into three types. The factor names were set as the first type (N = 7): efficiency seeking type, the second type (N = 19): benefit seeking type, and the third type [(N = 6): cost-effectiveness seeking type. The characteristics of each type are Type 1:Types that recognize aspects that are efficient for both consumers and restaurants, Type 2: Types of recognizing aspects of being benefited from speed, convenience and benefit, Type 3: Although it contributes to labor cost savings, it appears to recognize price and quality aspects in the initial market, which is burdened by consumers. The purpose of this study is to derive the problems of food delivery agency service business according to the three types and to provide strategic implications for the development direction and improvement plan.

• Journal of Korean Society of Transportation
• /
• v.32 no.5
• /
• pp.452-461
• /
• 2014

Conventional parking survey has been usually performed by a person, which has a lot of problems such as decreased mobility, data input error, longer time and expensiveness. Therefore, this study attempted to develop an automatic parking survey method using lately commercialized equipments that were highly efficient imagery interpretation equipments, GPS, and infrared lighting fixtures. In addition, this study developed a parking analysis software that enables to modify and save data, and analyze survey data by the automatic parking survey method. When parking survey is conducted using automatic parking survey method, surveying accuracy is influenced by the running speed of a surveying vehicle, the photographing angle of an imagery interpretation equipment, the gap between parking vehicles and the distance of a surveying vehicle to parking vehicles. Therefore, this study drew optimum conditions by testing on each items for accuracy improvement, and developed a parking analysis software for systematic storage and management of parking survey data, supporting the parking analysis and output the parking analysis result.

• Journal of Internet Computing and Services
• /
• v.9 no.1
• /
• pp.43-54
• /
• 2008

In this paper, we implement an automatic entity information management system for smart refrigerator using RFID technology in which objects containing electronic tags are automatically identified using radio wave. Unlike current "smart" refrigerators, the system presented in this paper implements smart tag information acquisition mechanism and real-time information management system to provide various information on entities in refrigerators to local and remote users. As the first step, this paper analyzes the requirements for smart refrigerator system based on the RFID and suggests design considerations. Based on the analysis, we propose and implement an efficient tag location tracking method based on antenna transfer method and an intelligent tag information management system based on embedded database and web server. We also provide a wide range of experimental results on the number of tags identified at a time and the tag recognition ratio according to the RFID antenna transfer speed and the angle between tag reader and tags.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.323-328
• /
• 2020

Recently, new approaches that significantly improve performance in object detection and recognition using deep learning technology have been proposed quickly. Of the various techniques for object detection, especially facial object detection (Faster R-CNN, R-CNN, YOLO, SSD, etc), SSD is superior in accuracy and speed to other techniques. At the same time, multiple object detection networks are also readily available. In this paper, among object detection networks, Mobilenet v2 network is used, models combined with SSDs are trained, and methods for detecting objects at a rate of four times or more than conventional performance are proposed using TensorRT engine, and the performance is verified through experiments. Facial object detector was created as an application to verify the performance of the proposed method, and its behavior and performance were tested in various situations.