• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.1
• /
• pp.169-189
• /
• 2015

Detection of anomalous events from video streams is a challenging problem in many video surveillance applications. One such application that has received significant attention from the computer vision community is traffic video surveillance. In this paper, a Lossy Count based Sequential Temporal Pattern mining approach (LC-STP) is proposed for detecting spatio-temporal abnormal events (such as a traffic violation at junction) from sequences of video streams. The proposed approach relies mainly on spatial abstractions of each object, mining frequent temporal patterns in a sequence of video frames to form a regular temporal pattern. In order to detect each object in every frame, the input video is first pre-processed by applying Gaussian Mixture Models. After the detection of foreground objects, the tracking is carried out using block motion estimation by the three-step search method. The primitive events of the object are represented by assigning spatial and temporal symbols corresponding to their location and time information. These primitive events are analyzed to form a temporal pattern in a sequence of video frames, representing temporal relation between various object's primitive events. This is repeated for each window of sequences, and the support for temporal sequence is obtained based on LC-STP to discover regular patterns of normal events. Events deviating from these patterns are identified as anomalies. Unlike the traditional frequent item set mining methods, the proposed method generates maximal frequent patterns without candidate generation. Furthermore, experimental results show that the proposed method performs well and can detect video anomalies in real traffic video data.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.3
• /
• pp.127-135
• /
• 2015

Context-aware mobile cloud computing is a new promising paradigm that allows to improve user experience by analyzing contextual information such as user location, time of the day, neighboring devices and current activity. In this paper we provide performance study of context-aware mobile cloud computing system with Volare middleware. Volare monitors the resources and context of the device. and dynamically adapts cloud service requests accordingly, at discovery time or at runtime. This approach allows for more resource-efficient and reliable cloud service discovery, as well as significant cost savings at runtime. We also have studied the performance of context-aware mobile cloud computing for different quality of service (QoS) adaptation policies. Our simulations results show that when battery level is low and CPU usage is high and user cannot maintain the initial QoS, service cost is decreased according to current adaptation policy. In conclusion, the current adaptation policy suggested in this paper may improve user experience by providing a dynamically adapted service cost according to a situation.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.9
• /
• pp.89-95
• /
• 2015

In this paper, we propose a real-time two-dimensional bar code detection system even at long range using a vision technique. We first perform short-range detection, and then long-range detection if the short-range detection is not successful. First, edge map generation, image binarization, and connect component labeling (CCL) are performed in order to select a region of interest (ROI). After interpolating the selected ROI using bilinear interpolation, a location symbol pattern is detected as the same as for short-range detection. Finally, the symbol pattern is arranged by applying inverse perspective transformation to localize bar codes. Experimental results demonstrate that the proposed system successfully detects bar codes at two or three times longer distance than existing ones even at indoor environment.

• Journal of the Korean Geographical Society
• /
• v.43 no.1
• /
• pp.52-70
• /
• 2008

Using MD Property View database on 15 counties in Maryland in the U.S., this study attempts to explore the estimation process on the housing development capacity under the Maryland's urban growth management policy known as the Smart Growth Initiatives. This study also seeks to draw the implications of the estimated development capacity by individual counties on successful implementation of the urban growth management policy. The finding shows that this region has land for residential use enough to accommodate growth for the next 30 years. However, contrary to the goal of the Smart Growth Initiatives, a majority of development capacity is located not only outside the Priority Funding Area designated by the Smart Growth Initiatives but also at counties that are located far away from the major metropolitan area. In addressing this problem, the state does not need to either abolish or immediately expand the Priority Funding Area. Rather, the state requires local governments to include housing elements in their comprehensive planning, to provide periodic estimates on housing and employment capacity, and to establish and manage database on the location and the capacity of developable land.

• Journal of Korea Game Society
• /
• v.16 no.6
• /
• pp.131-142
• /
• 2016

Recently, a variety of methodologies based on the use of educational coding robots have been proposed and experimented in newly emerging korean educational coding markets. Due to imprecise movement accuracy of the existing coding robots, however, such robots are mainly used as a toy. Inspired by these observations, we developed a simple adjustment method during robot movements, which is based on the observation results of 6 line-tracking sensors: 3 sensors in the center of a robot and other 3 sensors at the front. These sensors help to determine whether the robot is in the right location and whether it rotates as expected. Through the well-designed experiments, we report the effectiveness of our proposed solution: the average distance error of 1.57cm and the average degree error of 2.38 degree before and after complex movements. In near future, we hope our method to be popularly used in various educational coding robot platforms.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.9
• /
• pp.959-966
• /
• 2015

In this paper, we propose an indoor visible light communication(VLC) localization using Walsh code which can identify overlapped signals transmitted from the different LED sources as each of orthogonal signal at a receiver and using Manchester code which can eliminate the flicker of LED light and maintain a constant brightness. The proposed system can estimate the relative position of the receiver by using Lambertian radiation properties and trilateration method that are applied to the location information of fixed LED sources and the received signals from them. In order to verify the feasibility of the proposed system, we carried out the simulation in an indoor space with $6{\times}6{\times}1.5m^3$ installed LED lamps of 16. The simulation result shows that the proposed method achieves an average positioning error of 0.0536 m and a maximum positioning error of 0.2977 m.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.9 no.1
• /
• pp.19-28
• /
• 2007

Tunnel management is a time-consuming and expensive task. In particular, visual analysis of tunnel inspection often requires extended time and cost and shows problems on data gathering, storage and analysis. This study proposes a new approach to extract information for tunnel management by using a laser scanning technology. A prototype tunnel laser scanner developed was used to obtain point clouds of a railway tunnel surface. Initial processing of laser scanning data was to separate those laser pulses returned from the installations attached to tunnel liner using radiometric and geometric characteristics of laser returns. Once the laser returns from the installations were separated and removed, physically damaged parts on tunnel lining are detected. Based on the plane formed by laser scanner data, damaged parts are detected by analysis of proximity. The algorithms presented in this study successfully detect the physically damaged parts which can be verified by the digital photography of the corresponding location on the tunnel surface.

• Journal of Korea Multimedia Society
• /
• v.9 no.1
• /
• pp.89-100
• /
• 2006

The introduction of GSMP open interface to OBS network can materialize to separate the transport plane and the control plane in OBS network. This makes the implementation of OBS switches simple and provides various flexibility. However, the introduction of open interface will cause the connection setup delay because of the additional processing overhead of open interface protocol. Also, in GSMP based network, the location of network management functions are not defined explicitly and the research result about the OBS network management is almost nothing. This paper proposes a parallel connection setup mechanism using centralized connection control server to minimize connection setup delay in OBS network with GSMP open interface and defines managed objects to support connection, configuration, performance, and fault management for the management of OBS network with GSMP open interface. This paper also proposes a distributed network management model, in which the above managed objects are distributed in a controller and an OBS switch according to network management functions. We verify the possibility of OBS control and network management by implementing network management function using proposed parallel connection setup mechanism and distributed network management model.

• Journal of Advanced Navigation Technology
• /
• v.16 no.2
• /
• pp.264-270
• /
• 2012

e-Training focusing on the experience and practice accelerates actual-active learning and enforces the learning effects against the existing theory based education. The most typical hans-on training system is augmented reality. Especially, in the training field installed augmented reality system, the automobile maintenance trainee experiences effective training with the immediate information, which is indicating the location of parts and the procedure of repairing. The tracking is the core technology of the augmented reality system. The performance of augmented reality system depends on the tracking technology. Therefore, this paper suggests the tracking technology which is proper to the e-Training augmented reality service technology for the car mechanics.

• Journal of Korean Library and Information Science Society
• /
• v.6
• /
• pp.53-103
• /
• 1979

Kyujang-gak was an institution established by the King Jungjo's order to enshrine and edit the royal writings and autographs, and to help the revival of learning with more active services in collection, control, and use of the important materials. Furthermore, it was aimed in its establishment to promote the settlement of an innovative and ideal Royal Regime. In this paper, the Outer Kyujang-gak(外奎章閣) of Kangwha Magistracy(江華府), which was one of the lower branches of the Kyujanggak(奎章閣), will be treated, especially about its details of establishment, location, functions, the characteristics and value of its collection. After the Japanese invasion of Korea in 1592, the Historical Deposit Library(史庫) was established at the Kangwha Magistracy to take custody of the royal writings and autographs. An Annex(別庫) was built near by the Historical Deposit Library to enlarge the space in the reign of the King Hyojong. These spaces, however, become insufficient as the amount of materials deposited expanded, and custody for them was also not successful. Therefore, at the April of the 6th year of the King Jungjo's rule, the Outer Kyujang-gak was built at the east of the Temporary Palace(行宮) within Kangwha Magistracy, where the royal materials were deposited. This Outer Kynjang-gak was also called 'Kangdo Oe-gak(江都外閣)', 'Kyujang Oe-gak(奎章外閣)' or 'Simdo Oe-gak(心都外閣)', and its major function was to take custody of the materials and to hand them down to the next generations forever. The Kandwha Magistrate(江華留守) was responsible for the management of the Outer Kyujang-gak. Regular events for the book keeping were enshrinement, inventory and airing. In the 6th year in the reign of the King Jungjo, 4,892 volumes consisting of 762 titles were moved here from the Bon-gmodang(奉謨堂), the Seoseo(西序) in Main Palace, the Annex(別庫), the Deposit Library(史庫) mentioned above, the Kaegsa(客舍) and Chaeg-go(冊庫) within Kangwha Magistracy. By the end of the Joseon Dynasty, through fourteen times of addition altogether, the number of collection enshrined here reached 6,400 volumes consisting of 1,212 titles. The significance of this Outer Kyujang-gak established at the Kangwha Magistracy is in the point that this was one of the most important deopsit libraries of the Joseon Dynasty.