• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.681-686
• /
• 2003

In recent years automatic image indexing and retrieval have been increasingly studied. However, content-based retrieval techniques for general images are still inadequate for many purposes. The novelty and originality of this thesis are the definition and use of a spatial information model as a contribution to the accuracy and efficiency of image search. In addition, the model is applied to represent color and shape image contents as a vector using the method of image features extraction, which was inspired by the previous work on the study of human visual perception. The indexing scheme using the color, shape and spatial model shows the potential of being applied with the well-developed algorithms of features extraction and image search, like ranking operations. To conclude, user can retrieved more similar images with high precision and fast speed using the proposed system.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.218-224
• /
• 1998

The coefficients of variation obtained from three typical vegetation indices of eight levels of multi-spatial resolution images in urban areas were employed to identify the optimum spatial resolution in terms of maintaining information quality. These multi-spatial resolution images were prepared by degrading 1 meter simulated, 16 meter ADEOS/AVNIR, and 30 meter Landsat-TM images. Normalized Difference Vegetation Index (NDVI), Perpendicular Vegetation Index (PVI) and Soil Adjusted Ratio Vegetation Index (SARVI) were applied to reduce data redundancy and compare the characteristics of multi-spatial resolution image of vegetation indices. The threshold point on the curve of the coefficient of variation was defined as the optimum resolution level for the analysis with multi-spatial resolution image sets. Also, the results from the image segmentation approach of region growing to extract man-made features were compared with these multi-spatial resolution image sets.

• Journal of Korea Spatial Information System Society
• /
• v.9 no.1
• /
• pp.45-57
• /
• 2007

Recently, the development of sensor devices has accelerated researches on advanced technologies like Wireless Sensor Networks. Moreover, spatial sensors using GPS lead to the era of the Ubiquitous Computing Environment which generally uses spatial information and non-spatial information together. In this new era, a real-time processing system for spatial sensor data is essential. In this reason, new data processing systems called DSMS(Data Stream Management System) are being developed by many researchers. However, since most of them do not support geometry types and spatial functions to process spatial sensor data, they are not suitable for the Ubiquitous Computing Environment. For these reasons, in this paper, we designed and implemented a spatial DSMS by extending STREAM which stands for STanford stREam datA Manager, to solve these problems. We added geometry types and spatial functions to STREAM in order to process spatial sensor data efficiently. In addition, we implemented a Spatial Object Manager to manage shared spatial objects within the system. Especially, we implemented the Simple Features Specification for SQL of OGC for interoperability and applied algorithms in GEOS to our system.

• Journal of the Korean housing association
• /
• v.28 no.1
• /
• pp.1-8
• /
• 2017

Korea is experiencing unprecedented destruction of communities and crisis of mental health represented by top suicide rate among OECD countries. Its causes are manifold of various factors. One of them is lack of social support and broken communities that are closely related to social capital that is linked to other health indicators such as mortality rates. This studies looks for ways to improve social capital through spatial structure and features especially social capital related to neighborhood. Researchers conducted research literature review and observation on physical features of neighborhood streets and alleys. Review of studies show housing types can affect social capital level. High-rise apartments are related with lower neighborhood related social capital compared to single homes and low-rise multi-housing. Studies that mainly examined the physical features such as street layout showed that social encounters happened around local stores and crossings of small roads. Researchers identified actual streets that are more likely to be related with social activities in the neighborhood. Those streets were with physical elements that helped social exchange such as narrower streets, exposed stairs, street furniture of residents, parks, crossing of streets while other streets were with wider and easier access of cars.

• Journal of Computing Science and Engineering
• /
• v.10 no.2
• /
• pp.39-50
• /
• 2016

In this paper, we present a comparative study of spatial domain features for writer identification and verification with different ink width conditions. The existing methods give high error rates, when comparing two handwritten images with different pen types. To the best of our knowledge, we are the first to design the feature with different ink width conditions. To address this problem, contour based features were extracted using a chain code method. To improve accuracy at higher levels, we considered histograms of chain code and variance in bins of histogram of chain code as features to discriminate handwriting samples. The system was trained and tested for 1,000 writers with two samples using different writing instruments. The feature performance is tested on our newly created dataset of 4,000 samples. The experimental results show that the histogram of chain code feature is good compared to other methods with false acceptance rate of 11.67%, false rejection rate of 36.70%, average error rates of 24.18%, and average verification accuracy of 75.89% on our new dataset. We also studied the effect of amount of text and dataset size on verification accuracy.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.6C
• /
• pp.610-618
• /
• 2002

This paper presents a new image retrieval method that is based on color space and block region information. The color space information of images can be obtained by color binary set, and the block region information can be obtained by regional segmentation and feature. The candidate images are decided by comparing with color features and its binary set of query image and image feature database for retrieval. Particularly, it is possible that the retrieval using similarity-measurements has the weights of color spatial distribution arid its objective block region features. This retrieval method using color spatial and block region features is shown with the effectiveness on the result of implementation on image database with 6,000 images.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.3
• /
• pp.603-614
• /
• 1999

As multimedia application services on high-speed information network have been rapidly developed, the need for the video information management system that provides an efficient way for users to retrieve video data is growing. In this paper, we propose a video data model that integrates free annotations, image features, and spatial-temporal features for video purpose of improving content-based retrieval of video data. The proposed video data model can act as a generic video data model for multimedia applications, and support free annotations, image features, spatial-temporal features, and structure information of video data within the same framework. We also propose the video query language for efficiently providing query specification to access video clips in the video data. It can formalize various kinds of queries based on the video contents. Finally we design and implement the query processing engine for efficient video data retrieval on the proposed metadata model and the proposed video query language.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1148-1155
• /
• 2020

Fire must be extinguished as quickly as possible because they cause a lot of economic loss and take away precious human lives. Especially, the detection of smoke, which tends to be found first in fire, is of great importance. Smoke detection based on image has many difficulties in algorithm research due to the irregular shape of smoke. In this study, we introduce a new real-time smoke detection algorithm that reduces the detection of false positives generated by irregular smoke shape based on faster r-cnn of factory-installed surveillance cameras. First, we compute the global frame similarity and mean squared error (MSE) to detect the movement of smoke from the input surveillance camera. Second, we use deep learning algorithm (Faster r-cnn) to extract deferred candidate regions. Third, the extracted candidate areas for acting are finally determined using space and temporal features as smoke area. In this study, we proposed a new algorithm using the space and temporal features of global and local frames, which are well-proposed object information, to reduce false positives based on deep learning techniques. The experimental results confirmed that the proposed algorithm has excellent performance by reducing false positives of about 99.0% while maintaining smoke detection performance.

• Journal of Fisheries and Marine Sciences Education
• /
• v.23 no.3
• /
• pp.477-485
• /
• 2011

For the identifying of spatial distribution pattern, Moran's Index(I) which has the range of values from -1 to +1 is common method for the spatial autocorrelation measurement. When I is close to 1, all neighboring features have close to the same value, indicating clustered pattern. Conversely, if the spatial pattern is dispersed, I is close to -1. And I closing to 0 means spatially random pattern. However, this index equation is influenced by how defining the neighboring features for target feature. To compare and understand the difference of neighborhood definition methods, fixed distance neighboring method and Gabriel Network method were used for I. In this study, these two methods were applied to two marine environments with water quality data. One is Gwangyang Bay which has complex geometric coastal structure located in South Sea of Korea. Another is Uljin area adjacent to open sea located in east coast of Korea. The distances between water quality observed locations were relatively regular in Gwangyang Bay, however, irregular in Uljin area. And for the fixed distance method popular Arc GIS tool was used, but, for the Gabriel Network, Visual Basic program was developed to produce Gabriel Network and calculate Moran's I and its Z-score automatically. According to this experimental results, different spatial pattern was showed differently for some data with using of neighboring definition methods. Therefore there is need to choose neighboring definition method carefully for spatial pattern analysis.

• Spatial Information Research
• /
• v.11 no.2
• /
• pp.171-184
• /
• 2003

Lots of application systems are developed for applying business GIS in marketing or strategic planning of the company, recently. Almost of the systems require statistics for some areas(trade areas or sales areas) as the important information of decision support. As far as now, trade areas are defined for individual stores using know-how of the specialists, but there is no well-defined method for defining of trade areas of the specific business domains or trade areas of the customers. In this study, we have applied the spatial data mining methods to the point features in GIS, evaluated the results of each methods, and discussed the feasibility of defining of trade areas. From the results of this study, we have concluded that the defining of trade areas from point features, such as franchisees of credit card company or memberships of retail chain store, and that the DENCLUE(DENsity-based CLUstEring) method is the best suitable spatial data mining algorithm for this purpose.