• The KIPS Transactions:PartB
• /
• v.17B no.5
• /
• pp.355-362
• /
• 2010

Face tracking is to estimate the motion of a non-rigid face together with a rigid head in 3D, and plays important roles in higher levels such as face/facial expression/emotion recognition. In this paper, we propose an AAM-based face tracking algorithm. AAM has been widely used to segment and track deformable objects, but there are still many difficulties. Particularly, it often tends to diverge or converge into local minima when a target object is self-occluded, partially or completely occluded. To address this problem, we utilize the scale invariant feature transform (SIFT). SIFT is an effective method for self and partial occlusion because it is able to find correspondence between feature points under partial loss. And it enables an AAM to continue to track without re-initialization in complete occlusions thanks to the good performance of global matching. We also register and use the SIFT features extracted from multi-view face images during tracking to effectively track a face across large pose changes. Our proposed algorithm is validated by comparing other algorithms under the above 3 kinds of occlusions.

• The Journal of the Korea Contents Association
• /
• v.14 no.5
• /
• pp.425-435
• /
• 2014

The research for extracting man-made features such as building and road from the aerial photograph or satellite imagery has been performed actively. As lately the resolution of digital aerial photographs was improved, unwanted features(noise) would be often detected. An edge detection algorithm is developed to make up for such a noise problem, make boundaries of wanted objects clear and extract only needed features. The algorithm developed in this research performs separating RGB channels, differencing between channels, transforming in to binary images, excluding noises and restoring shapes, and edge extraction in order. The images to be used for edge detection are prepared through bundle adjustment, DTM extraction, orthorectification and mosaicking. The roof edges of small building on preprocessed digital aerial orthophotos were extracted using the algorithm developed in this study. The validity of the algorithms was proved by comparing edge results of small building extracted in this study with those of conventional methods.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.22 no.3
• /
• pp.209-222
• /
• 1997

In this paper, we study a bargaining order problem where one buyer sequentially bargains with two sellers whose reservation prices are unknown to the buyer but correlated. Our main question is who the buyer should bargain first with to maximize his expected payoff. This type of problem is widely applicable to business and political situations where one party negotiates with multiple parties sequentially. One of the most important element in a sequential bargaining is "linkage effect" which exists when the aggreement of the previous bargaining affects the outcome of the following bargaining. To examine "linkage effect", we assume that the sellers'objects are similar so that the sellers' reservation prices are correlated. In addition, to consider incomplete information aspect regarding reservation prices, it is assumed that the sellers' reservation prices are unknown to the buyer. That is, we deal with one sided incomplete information case. In our model, there are two stages in each of which the buyer meets one seller. Since we are concerned with the bargaining order, we consider two different bargaining orders. Using game theory, we find a perfect Bayesian equilibrium and compute the buyer's expected payoff for each bargaining order. Finally we identify the advantageous bargaining order for the buyer by comparing the expected payoffs obtained under two different bargaining orders. Our results are as follows: the advantageous bargaining order depends on the prior probability of the seller type. However, in general, the buyer should bargain first with the seller whose object is less valuable to the buyer. The basic reason for our result is that the buyer wants to experiment in the first stage to find out the sellers' reservation prices and in doing so, to minimize the experimental cost and maximize potential gain in case of negotiation failure in the first stage. in the first stage.

• The Journal of the Korea Contents Association
• /
• v.6 no.8
• /
• pp.133-143
• /
• 2006

Today, most of games permit interaction between user and game freely. Therefore it is difficult to progress the story-line of the primary stage. Especially in educational game surroundings, we have more difficulties in achieving original purpose of education. In this paper, we proposed the applied model of mini-game which was inserted into main-game in order to control interaction between user and game. On the basis of this model, we derived valuation elements by mini-game implementation types from developing the educational game in which involved mini-game. We looked around whether the educational game achieved the educational goal of first stage or not. Comparing with some excellent ones picked up by public authorities, we evaluated the educational game. As the result of evaluation, we could find that the application of mini-game had very high effectiveness in attainment of teaming goal, studying of well-balanced, and induction of learning motivation. And we found that the application also had very affirmative effect to the practical objects of primary stage in overall sphere.

• Journal of Navigation and Port Research
• /
• v.31 no.6
• /
• pp.523-530
• /
• 2007

Crane systems are very important in industrial fields to carry heavy objects such that many investigations about control of the systems are actively conducted for enhancing its control performance. This paper presents an adaptive control approach using the model matching for a complex 3-DOF nonlinear crane system. First, the system model is linearized through feedback linearization method and then PD control is applied in the approximated model. This linear model is considered as nominal to derive corrective control law for a perturbed crane model using Lyapunov theory. This corrective control is primitively aimed to compensate real-time control deviation due to partially known perturbation. We additionally study stability analysis of the crane control system using Lyapunov perturbation theory. Evaluation of our control approach is numerically carried out through computer simulation and its superiority is demonstrated comparing with the classical control.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.2
• /
• pp.205-214
• /
• 1997

In this paper, we suggest a cache mechanism to improve the speed fo query processing in distributed directory environment. For this, request and result and result about objects in remote site are store in the cache of local site. A cache mechanism developed through six phases; 1) Cached information which stored in distributed directory system is classified as application data, system data and meta data. 2) Cache system architecture is designed according to classified information. 3) Cache schema are designed for each cache information. 4) Least-TTL algorithms which use the weighted value of geograpical information and access frquency for replacements are developed for datacaches(application cache, system cache). 5) Operational algorithms are developed for meta data cache which has meta data tree. This tree is based on the information of past queries and improves the speed ofquery processing by reducing the scope of search space. 6) Finally, performance evaluations are performed by comparing with proposed cache mechanism and other mechanisms.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.12
• /
• pp.400-406
• /
• 2016

Comparing the past and the present in agriculture, society is losing people who work in farming, and the age of those who remain is increasing. Farmers are interested in special crops if the agricultural products' costs are low and the crops are easy to grow. If the area where a crop grows is bad, the agricultural products' quality gets worse. To overcome this situation, a new approach is being tried with crops. This research offers new technology to the young generation. This paper proposes technology that uses Internet of Things techniques to automatically sparge water and pesticide on orchards and fields using a machine instead of a person. We used the open source Arduino and sensor modules to build the automatic system. In this research, a circuit was simplified, and we constructed the proper size of the system by preventing errors in sensors, keeping distance from objects, and minimizing circuit collision. The machine drives and turns its head to sparge agricultural pesticides. The machine will minimize harmful effects caused by pesticides on humans, and will be helpful to farmers.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.426-429
• /
• 2006

Flood caused by Typhoon and severe rain during summer is the most destructive natural disasters in Korea. Almost every year flood has resulted in a big lost of national infrastructure and loss of civilian lives. It usually takes time and great efforts to estimate the flood-related damages. Government also has pursued proper standard and tool for using state-of-art technologies. High resolution satellite imagery is one of the most promising sources of ground truth information since it provides detailed and current ground information such as building, road, and bare ground. Once high resolution imagery is utilized, it can greatly reduce the amount of field work and cost for flood related damage assessment. The classification of high resolution image is pre-required step to be utilized for the damage assessment. The classified image combined with additional data such as DEM and DSM can help to estimate the flooded areas per each classified land use. This paper applied object-oriented classification scheme to interpret an image not based in a single pixel but in meaningful image objects and their mutual relations. When comparing it with other classification algorithms, object-oriented classification was very effective and accurate. In this paper, IKONOS image is used, but similar level of high resolution Korean KOMPSAT series can be investigated once they are available.

• Journal of International Academy of Physical Therapy Research
• /
• v.3 no.1
• /
• pp.391-396
• /
• 2012

The purpose of this study is to identify which width of the base of support(BOS) is safer and more effective in lifting by comparing muscle activations and body sways when lifting objects under the width variation of the BOS. A total of fifteen healthy adults participated in this study. For the width variation of the BOS, the participants changed the width between their feet into three different types(10cm, 32cm, 45cm) and lifted a 10kg four times in each type after going up on a force plate. In order to measure body sways according to the width variation of the BOS, a motion analysis system was used. In addition, in order to measure the muscle activations of lower extremities, including the erector spinae, gluteus maximus, rectus femoris, and tibialis anterior, an electromyogram(EMG) analysis was employed. In addition, the Borg's scale was drawn by quantifying the subjective discomfort levels felt from each width of the BOS. In conclusion, no statistically significant differences according to the width variation of the BOS were observed(p=.295, .308)(p>.05). However, a statistically significant difference was exhibited between the Borg's scale, which indicates the discomfort levels from lifting performances, and the width variation of the BOS (p=$.000^*$).

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.6 s.44
• /
• pp.289-298
• /
• 2006

Many researches are going on with regard to issues and problems related to mobile database systems, which are caused by the weak connectivity of wireless networks, the mobility and the portability of mobile clients. Mobile computing satisfies user's demands for convenience and performance to use information at any time and in any place, but it has many problems to be solved in the aspect of data management. The purpose of our study is to design Mobile Continuous Query Processing System(MCQPS) to solve problems related to database hoarding, the maintenance of shared data consistency and the optimization of logging, which are caused by the weak connectivity and disconnection of wireless networks inherent in mobile database systems under mobile client server environments. We proved the superiority of the proposed MCQPS by comparing its performance to the C I S(Client-Intercept-Slaver) model. In Addition, we experiment on proposed index structure and methodology in various methods.