• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• pp.186-198
• /
• 2021

Security control using surveillance cameras is established when people observe all surveillance videos directly. However, this task is labor-intensive and it is difficult to detect all abnormal situations. In this paper, we propose a deep neural network model, called AT-Net, that automatically detects abnormal situations in the surveillance video, and introduces an automatic video surveillance system developed based on this network model. In particular, AT-Net alleviates the ambiguity of existing abnormal situation detection methods by mapping features representing relationships between people and objects in surveillance video to the new tensor structure based on sparse coding. Through experiments on actual surveillance videos, AT-Net achieved an F1-score of about 89%, and improved abnormal situation detection performance by more than 25% compared to existing methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.648-649
• /
• 2022

Glass is a common object in living environments, but even humans are sometimes unable to identify it. This study proposes a method for detecting glass area by learning edge information from images. The network structure of Transformer is used to accept the base features extracted by backbone and extract the boundary information of RGB images, and both features are used to learn the features of glass area and determine the glass area based on these boundary features. The experimental results show that our proposed method can detect glass area in images.

• Journal of KIISE:Databases
• /
• v.31 no.6
• /
• pp.624-640
• /
• 2004

Recently, with the rapid development of location-based techniques, index structures to efficiently manage moving objects have been required. In this paper, we propose a new spatio-temporal index structure that supports a future position retrieval and minimizes a update cost. The proposed index structure combines an assistant index structure that directly accesses current positions of moving objects with KDB-tree that is a space partitioning access method. The internal node in our proposed index structure keeps time parameters in order to support the future position retrieval and to minimize a update cost. Moreover, we propose new update and split methods to maximize the space utilization and the search performance. We perform various experiments to show that our proposed index structure outperforms the existing index structure.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.10C
• /
• pp.958-966
• /
• 2003

Change detection algorithms based on frame difference are frequently used for finding moving objects in image sequences. These algorithms detect the change of frames using estimated statistical background model. But, if this estimated background model is different from the actual statistical distribution, false detections are generated. In this paper, we propose an improved change detection algorithm using euler number and structure tensor. The proposed mapping method which is based on the euler number can be used for reducing the false detections that generated by nonparametric change detection algorithm. In this paper, the change in the region of moving object also can be detected by the proposed method using structure tensor. Experimental result shows that the proposed method reduces the false detections effectively by 90% on "Weather", by 34% on "Mother & daughter" and by 43% on "Aisle" than an existing method does.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.2
• /
• pp.91-99
• /
• 2014

This paper is about design and implementation of 'SeaMap' importer module which is for map-based application using 'SeaMap' data. 'SeaMap' data importer is a module that reads 'SeaMap' data in consistent form and offers using easily change the format and the internal data structure in the application. Design of data importer module is based on analyzing characteristic of 'SeaMap'. The comparative analysis between the data type of 'SeaMap' and standard S-57 Electronic Navigation Chart (ENC) of the International Hydrographic Organization (IHO), based on this, to be applicable of S-52 standards 'SeaMap' data is defined as a structure of data. The importer module is designed and converted to allow to use distribution type of 'SeaMap' data sets in map application, parsing 'SeaMap' data around the object defining transformation data structure. In addition, we implemented a 'SeaMap' data viewer in order to test our 'SeaMap' data importer module.

• Journal of Korea Multimedia Society
• /
• v.14 no.2
• /
• pp.318-328
• /
• 2011

This paper suggests a comprehensive method to describe architectural components for supporting Korean Traditional Building design with only small components set in CAD system. Korean traditional buildings can be classified variously based on the their size, usage and structure type(whether ornament part, namely Gongpo, is in there or not). Moreover components can be varied according to the combining rule between them. If all of these components are presented, these tremendous components rather prevent the efficient design of traditional buildings. In order to solve this problem we present object-oriented approach to describe versatile components as one template if they are same in functional aspects. From the template, many similar instances can be derived according to the attribute value. The templates are designed in order to reflect the coupling scheme between components in the relative parameters of the templates. It leads effects of minimizing error which can be occurred frequently in the process of traditional building design.

• Journal of the Korea Computer Graphics Society
• /
• v.7 no.1
• /
• pp.1-9
• /
• 2001

We present a scheme and a data structure that decompose the space into adaptive-sized cells to improve the visualization of soft objects. Soft objects are visualized through the evaluation of the field functions at every point of the space. According to the propsed scheme, the affecting soft objects for a point in the space is searched through the data structure called interval tree based on the bounding volume of the components, which represent a soft object whose defining primitive(skeleton) is a simple geometric object such as point or line segment. The bounding volume of each component is generated with respect to the radius of a local field function of the component, threshold value, and the relations between the components and other neighboring components. The proposed scheme can be used in many applications for soft objects such as modeling and rendering, especially in interactive modeling process.

• Nuclear Engineering and Technology
• /
• v.49 no.2
• /
• pp.395-403
• /
• 2017

An efficient evaluation method for the probability of a tornado missile strike without using the Monte Carlo method is proposed in this paper. A major part of the proposed probability evaluation is based on numerical results computed using an in-house code, Tornado-borne missile analysis code, which enables us to evaluate the liftoff and flight behaviors of unconstrained objects on the ground driven by a tornado. Using the Tornado-borne missile analysis code, we can obtain a stochastic correlation between local wind speed and flight distance of each object, and this stochastic correlation is used to evaluate the conditional strike probability, $Q_V(r)$, of a missile located at position r, where the local wind speed is V. In contrast, the annual exceedance probability of local wind speed, which can be computed using a tornado hazard analysis code, is used to derive the probability density function, p(V). Then, we finally obtain the annual probability of tornado missile strike on a structure with the convolutional integration of product of $Q_V(r)$ and p(V) over V. The evaluation method is applied to a simple problem to qualitatively confirm the validity, and to quantitatively verify the results for two extreme cases in which an object is located just in the vicinity of or far away from the structure.

• Journal of KIISE
• /
• v.43 no.2
• /
• pp.152-162
• /
• 2016

Most traditional garbage collectors commonly use the language level metadata, which is designed for pointer type searching. However, because it is difficult to use this metadata in non-volatile memory allocation platforms, a new garbage collection technique is essential for non-volatile memory utilization. In this paper, we design new metadata for managing information regarding non-volatile memory allocation called "Allocation Tree". This metadata is comprised of tree data structure for fast information lookup and a node that holds an allocation address and an object ID pair in key-value form. The Garbage Collector starts collecting when there are insufficient non-volatile memory spaces, and it compares user data and the allocation tree for garbage detection. We develop this algorithm in a persistent heap based non-volatile memory allocation platform called "HEAPO" for demonstration.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.3
• /
• pp.14-24
• /
• 1996

A fuzzy classifier which needs various analyses of features using genetic algorithms is proposed. The fuzzy classifier has a simple structure, which contains a classification part based on fuzzy logic theory and a rule generation ation padptu sing genetic algorithms. The rule generation part determines optimal fuzzy membership functions and inclusior~ or exclusion of each feature in fuzzy classification rules. We analyzed recognition rate of a specific object, then added finer features repetitively, if necessary, to the object which has large misclassification rate. And we introduce repetitive analyses method for the minimum size of string and population, and for the improvement of recognition rates. This classifier is applied to three examples of the classification of iris data, the discrimination of thyroid gland cancer cells and the recognition of confusing handwritten and printed numerals. In the recognition of confusing handwritten and printed numerals, each sample numeral is classified into one of the groups which are divided according to the sample structure. The fuzzy classifier proposed in this paper has recognition rates of 98. 67% for iris data, 98.25% for thyroid gland cancer cells and 96.3% for confusing handwritten and printed numeral!;.