• Journal of the Korean Data and Information Science Society
• /
• v.19 no.3
• /
• pp.979-994
• /
• 2008

Moving objects are spatio-temporal data that change their location or shape continuously over time. Generally, if continuously moving objects are managed by a conventional database management system, the system cannot properly process the past and future location which is not stored in the database. Up to now, for the purpose of location tracking which is not stored, the linear interpolation to estimate the past location has been usually used. It is suitable for the moving objects on linear route, not curved route. In this paper, we propose a past location tracking algorithm for a moving object on curved routes, and also suggest a future location tracking algorithm using some past location information. We found that the proposed location tracking algorithm has higher accuracy than the linear interpolation function.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.83-86
• /
• 2002

최근 지리 정보 시스템이나 공간 데이터 베이스 시스템이 발전하면서 실세계를 효율적으로 모델링하려는 맡은 연구가 수행되고 있다. 기존의 단순한 point, line, polygon으로 모델링했던 방법들을 multipoint, multiline, multipolygon과 같은 복잡한 객체를 표현하기 위한 연구로 확장되었다. 또한 이러한 공간 객체의 이력을 효율적으로 관리하기 위해 공간 객체를 시간으로 확장하는 연구가 수행되고 있다. 이러한 모델들은 명확한 경계를 가진 시공간 객체를 대상으로 한다. 자연, 사회 문화 현상, 생태 같은 경계가 명확하지 않은 객체를 단순한 경계를 가진 공간 객체로 모델링하기에는 그 표현력이 부족하다. 따라서 이 논문에서는 이런 문제점을 해결하기 위해서 불확실한 경계를 가진 시공간 데이터 모델을 제시한다. 이 논문에서 제시한 불확실한 경제를 가진 시공간 모델의 설계는 상호 운용을 증진하기 위하여 OGC(OpenGIS Consortium)에서 제시한 2차원 기하 객체 모델을 기반으로 불확실한 경계를 가지는 공간 데이터 모델로 확장한다. 또한, 이 불확실한 경계를 가지는 단순한 공간 모델을 시간 영역으로 확장하여 유효시간을 갖는 불확실한 시공간 데이터 모델을 설계한다. 또한, 이 논문에서 제시한 불확실한 경계를 가진 시공간 객체 모델을 바탕으로 실세계의 다양하고 복잡한 객체에 대한 효율적인 질의가 가능한 시공간 연산자를 제시한다.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.65-75
• /
• 2005

Moving-objects databases should efficiently support database queries that refer to the trajectories and positions of continuously moving objects. To improve the performance of these queries. an efficient indexing scheme for continuously moving objects is required. To my knowledge, range queries on current positions cannot be handled by the 3D R-tree and the TB-tree. In order to handle range queries on current and past positions. I modified the original 3D R-tree to keep the now tags. Most of spatio-temporal index structures suffer from the fact that they cannot efficiently process range queries past positions of moving objects. To address this issue. we propose an access method, called the Tagged Adaptive 3DR-tree (or just TA3DR-tree), which is based on the original 3D R-tree method. The results of our extensive experiments show that the Tagged Adaptive 3DR-tree outperforms the original 3D R-tree and the TB-tree typically by a big margin.

• Journal of KIISE:Databases
• /
• v.31 no.6
• /
• pp.664-674
• /
• 2004

The trajectory preservation property that stores only one trajectory in a leaf node is the most important feature of an index structure, such as the TB-tree for retrieving object's moving paths in the spatio-temporal space. It performs well in trajectory-related queries such as navigational queries and combined queries. But, the MBR of non-leaf nodes in the TB-tree have large amounts of dead space because trajectory preservation is achieved at the sacrifice of the spatial locality of trajectories. As dead space increases, the overlap between nodes also increases, and, thus, the classical range query cost increases. We present a new split policy and entry relocation policies, which have no deterioration of the performance for trajectory-related queries, for improving the performance of range queries. To maximally reduce the dead space of a non-leaf node's MBR, the Maximal Area Reduction (MAR) policy is used as a split policy for non-leaf nodes. The entry relocation policy induces entries in non-leaf nodes to exchange each other for the purpose of reducing dead spaces in these nodes. We propose two algorithms for the entry relocation policy, and evaluate the performance studies of new algorithms comparing to the TB-tree under a varying set of spatio-temporal queries.

• Journal of Korea Spatial Information System Society
• /
• v.8 no.1 s.16
• /
• pp.59-75
• /
• 2006

One of the most challenging and encouraging applications of state-of-the-art technology is the field of traffic control systems. It combines techniques from the areas of telecommunications and computer science to establish traffic information and various assistance services. The support of the system requires a moving objects database system (MODB) that stores moving objects efficiently and performs spatial or temporal queries with time conditions. In this paper, we propose schemes to distribute an index nodes of trajectory based on spatio-temporal proximity and the characteristics of moving objects. The scheme predicts the extendible MBB of nodes of index through the prediction of moving object, and creates a parallel trajectory index. The experimental evaluation shows that the proposed schemes give us the performance improvement by 15%. This result makes an improvement of performance by 50% per one disk.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2444-2463
• /
• 2020

Significant detection of video can more rationally allocate computing resources and reduce the amount of computation to improve accuracy. Deep learning can extract the edge features of the image, providing technical support for video saliency. This paper proposes a new detection method. We combine the Convolutional Neural Network (CNN) and the Deep Bidirectional LSTM Network (DB-LSTM) to learn the spatio-temporal features by exploring the object motion information and object motion information to generate video. A continuous frame of significant images. We also analyzed the sample database and found that human attention and significant conversion are time-dependent, so we also considered the significance detection of video cross-frame. Finally, experiments show that our method is superior to other advanced methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.12
• /
• pp.5015-5022
• /
• 2010

Most of the existing pattern mining techniques are capable of searching patterns according to the continuous change of the spatial information of an object but there is no constraint on the spatial information that must be included in the extracted pattern. Thus, the existing techniques are not applicable to the optimal path search between specific nodes or path prediction considering the nodes that a moving object is required to round during a unit time. In this paper, the precision of the path search according to the spatial hierarchy is analyzed using the Spatial-Temporal Optimal Moving Pattern(with Frequency & Weight) (STOPM(FW)) algorithm which searches for the optimal moving path by considering the most frequent pattern and other weighted factors such as time and cost. The result of analysis shows that the database retrieval time is minimized through the reduction of retrieval range applying with the spatial constraints. Also, the optimal moving pattern is efficiently obtained by considering whether the moving pattern is included in each hierarchical spatial scope of the spatial hierarchy or not.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.13 no.2
• /
• pp.41-53
• /
• 2010

Traffic safety assessment is often accomplished by analyzing the number of crashes occurring in some geographic space over certain specific time duration. In this paper, we introduce a procedure that can efficiently analyze spatial and temporal changes in traffic crashes before-and-after implementation of a certain traffic controlling measure. For the analysis, crash frequency data before-and-after closing a major highway around St. Louis in Missouri was collected through Transportation Management System(TMS) database that is maintained by Missouri Department of Transportation (MoDOT). In order to identify any spatial and temporal pattern in crashes, each crash is pinpointed on a map using the dynamic segmentation in GIS. Then, the identified pattern is statistically confirmed using an analysis of variance table. The advantage of this approach is to easily assess spatial and temporal trend of crashes that are not readily attainable otherwise. The results from this study can possibly be applied in enhancing the highway safety assessment procedure. This paper also makes several suggestions for future development of a comprehensive transportation data system in Korea which is similar to MoDOT's TMS database.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.2 s.46
• /
• pp.231-242
• /
• 2007

The existing pattern mining methods[1,2,3,4,5,6,11,12,13] do not use location generalization method on the set of location history data of moving object, but even so they simply do extract only frequent patterns which have no spatio-temporal constraint in moving patterns on specific space. Therefore, it is difficult for those methods to apply to frequent pattern mining which has spatio-temporal constraint such as optimal moving or scheduling paths among the specific points. And also, those methods are required more large memory space due to using pattern tree on memory for reducing repeated scan database. Therefore, more effective pattern mining technique is required for solving these problems. In this paper, in order to develop more effective pattern mining technique, we propose new location generalization method that converts data of detailed level into meaningful spatial information for reducing the processing time for pattern mining of a massive history data set of moving object and space saving. The proposed method can lead the efficient spatial moving pattern mining of moving object using by creating moving sequences through generalizing the location attributes of moving object into 2D spatial area based on $R^*$-Tree and Area Grid Hash Table(AGHT) in preprocessing stage of pattern mining.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.6 s.44
• /
• pp.9-17
• /
• 2006

Moving objects database systems manage a set of moving objects which changes its locations and directions continuously. The traditional spatial indexing scheme is not suitable for the moving objects because it aimed to manage static spatial data. Because the location of moving object changes continuously, there is problem that expense that the existent spatial index structure reconstructs index dynamically is overladen. In this paper, we analyzed the insertion/deletion costs for processing the movement of objects. The results of our extensive experiments show that the Dynamic Hashing Index outperforms the original R-tree and the fixed grid typically by a big margin.