• Journal of the Korea Convergence Society
• /
• v.8 no.6
• /
• pp.29-36
• /
• 2017

In this paper, we propose a method for generating improved saliency map by learning multiple features to improve the accuracy and reliability of saliency map which has similar result to human visual perception type. In order to overcome the inaccurate result of reverse selection or partial loss in color based salient area estimation in existing salience map generation, the proposed method generates multi feature data based on learning. The features to be considered in the image are analyzed through the process of distinguishing the color pattern and the region having the specificity in the original image, and the learning data is composed by the combination of the similar protrusion area definition and the specificity area using the LAB color space based color analysis. After combining the training data with the extrinsic information obtained from low level features such as frequency, color, and focus information, we reconstructed the final saliency map to minimize the inaccurate saliency area. For the experiment, we compared the ground truth image with the experimental results and obtained the precision-recall value.

• Korean Journal of Remote Sensing
• /
• v.24 no.4
• /
• pp.381-388
• /
• 2008

In the common practice of air-photographing measurement aerial-photogrammetric, the location of camera at the time of photographing is identified by performing aerotriangulation. However, installing ground-base station to enable aerotriangulation takes majority portion of a map making cost. Aerial-photogrammetric has shown a great improvement helped by steady upgrading in equipment and development in quantitative study. Aerotriangulation can be replaced by Direct Georeferencing, which uses GPS/INS to identify a camera location and to produce detailed information. An innovative technique replacing aerotriangulation, it has a disadvantage that base station has to be available in the area of photographing. The study intends to suggest a method applying VRS in GPS/INS aerotriangulation. Despite the fact that Direct Georeferencing is the innovated technique which substitutes existing aerotriangulation, it still need to install the ground-base station in GPS/INS aerotriangulation. GPS/INS data was analyzed with 4 different cases in order to accomplish the purpose of this study. In addition, in the thesis, it was approved that VRS can be utilized to make small-scale map as accurate as base station. This study is expected to improve the efficiency of work by showing that VRS can be used not only in base station but also enabling base station in the ground-access challenging area.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.1
• /
• pp.1-7
• /
• 2023

An artificial intelligence (AI) method based on image deep learning is proposed to predict the entire displacement shape of a structure using the feature of partial displacements. The performance of the method was investigated through a structural test of a steel frame. An image-to-image regression (I2IR) training method was developed based on the U-Net layer for image recognition. In the I2IR method, the U-Net is modified to generate images of entire displacement shapes when images of partial displacement shapes of structures are input to the AI network. Furthermore, the training of displacements combined with the location feature was developed so that nodal displacement values with corresponding nodal coordinates could be used in AI training. The proposed training methods can consider correlations between nodal displacements in 3D space, and the accuracy of displacement predictions is improved compared with artificial neural network training methods. Displacements of the steel frame were predicted during the structural tests using the proposed methods and compared with 3D scanning data of displacement shapes. The results show that the proposed AI prediction properly follows the measured displacements using 3D scanning.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.11
• /
• pp.53-62
• /
• 1994

This paper presents a new approach of analyzing errors resulting from nonideal general-purpose lighting environment when the Photometric Stereo Method (PSM) is applied to estimate the surface-orientation of a three-dimensional object. The approach introduces the explicit modeling of the lighting environment including a circular-disk type irradiance object plane and the direct simulation of the error distribution with the model. The light source is modeled as a point source that has a certain amount of beam angle, and the luminance distribution on the irradiance plane is modeled as a Gaussian function with different deviation values. A simulation algorithm is devised to estimate the light source orientation computing the average luminance intensities obtained from the irradiance object planes positioned in three different orientations. The effect of the nonideal lighting model is directly reflected in such simulation, because of the analogy between the PSM and the proposed algorithm. With an instrumental tool designed to provide arbitrary orientations of the object plane at the origin of the coordinate system, experiment can be performed in a systematic way for the error analysis and compensation. Simulations are performed to find out the error distribution by widely varying the light model and the orientation set of the object plane. The simulation results are compared with those of the experiment performed in the same way as the simulation. It is confirmed from the experiment that a fair amount of errors is due to the erroneous effect of the general-purpose lighting environment.

• Journal of Korea Water Resources Association
• /
• v.39 no.8 s.169
• /
• pp.677-690
• /
• 2006

The LH-OAT (Latin Hypercube One factor At a Time) method for sensitivity analysis and SCE-UA (Shuffled Complex Evolution at University of Arizona) optimization method were applied for the automatic calibration of SWAT model in Bocheong-cheon watershed. The LH-OAT method which combines the advantages of global and local sensitivity analysis effectively identified the sensitivity ranking for the parameters of SWAT model over feasible parameter space. Use of this information allows us to select the calibrated parameters for the automatic calibration process. The performance of the automatic calibration of SWAT model using SCE-UA method depends on the length of calibration period, the number of calibrated parameters, and the selection of statistical error criteria. The performance of SWAT model in terms of RMSE (Root Mean Square Error), NSEF (Nash-Sutcliffe Model Efficiency), RMAE (Relative Mean Absolute Error), and NMSE (Normalized Mean Square Error) becomes better as the calibration period and the number of parameters defined in the automatic calibration process increase. However, NAE (Normalized Average Error) and SDR (Standard Deviation Ratio) were not improved although the calibration period and the number of calibrated parameters are increased. The result suggests that there are complex interactions among the calibration data, the calibrated parameters, and the model error criteria and a need for further study to understand these complex interactions at various representative watersheds.

• Journal of Korean Home Economics Education Association
• /
• v.19 no.2
• /
• pp.115-129
• /
• 2007

The purpose of this study is to review the trends of education researches on the housing in Korea and Japan. It was based on the Journal of Korean Home Economics Education and Journal of the Japan Association of Home Economics Education. For the inquiry, 49 articles(20 from Korea and 29 from Japan) were collected from 1989 to 2006. The results of this study are as follows: First, the number of the articles of housing education was not quantitatively enough compared to the other fields in Korean and Japan. Second, regarding research fields, there were lots of articles about 'the perception of housing education' and 'teaching-learning method & teaching materials' in Korea. On the other hand in Japan, articles about 'teaching-learning method & teaching materials' and 'the evaluation of education' were major fields. Third, the major research topic was 'overall of the housing education' in Korea, while 'living space' in Japan. Fourth, the major data collecting method were questionnaire surveys and experiments, mostly targeting students and teachers from junior and high schools. Descriptive statistics such as frequencies, percentages and means were most often used for data analyses.

• Journal of KIISE:Databases
• /
• v.29 no.5
• /
• pp.367-380
• /
• 2002

Due to recent increase in applications requiring huge amount of data such as spatial data analysis and image analysis, clustering on large databases has been actively studied. In a hierarchical clustering method, a tree representing hierarchical decomposition of the database is first created, and then, used for efficient clustering. Existing hierarchical clustering methods mainly adopted the bottom-up approach, which creates a tree from the bottom to the topmost level of the hierarchy. These bottom-up methods require at least one scan over the entire database in order to build the tree and need to search most nodes of the tree since the clustering algorithm starts from the leaf level. In this paper, we propose a novel top-down hierarchical clustering method that uses multidimensional indexes that are already maintained in most database applications. Generally, multidimensional indexes have the clustering property storing similar objects in the same (or adjacent) data pares. Using this property we can find adjacent objects without calculating distances among them. We first formally define the cluster based on the density of objects. For the definition, we propose the concept of the region contrast partition based on the density of the region. To speed up the clustering algorithm, we use the branch-and-bound algorithm. We propose the bounds and formally prove their correctness. Experimental results show that the proposed method is at least as effective in quality of clustering as BIRCH, a bottom-up hierarchical clustering method, while reducing the number of page accesses by up to 26～187 times depending on the size of the database. As a result, we believe that the proposed method significantly improves the clustering performance in large databases and is practically usable in various database applications.

• Archives of design research
• /
• v.17 no.1
• /
• pp.211-220
• /
• 2004

The Chaos theory of complexity and Fractal theory which became a prominent figure as a new paradigm of natural science should be understood not as whole, and not into separate elements of nature. Fractal Dimensions are used to measure the complexity of objects. We now have ways of measuring things that were traditionally meaningless or impossible to measure. They are capable of describing many irregularly shaped objects including man and nature. It is compatible method of application to express complexity of nature in the dimension of non-fixed number by placing our point of view to lean toward non-linear, diverse, endless time, and complexity when we look at our world. Fractal Dimension allows us to measure the complexity of an object. Having a wide application of fractal geometry and Chaos theory to the art field is the territory of imagination where art and science encounter each other and yet there has not been much research in this area. The formative word has been extracted in this study by analyzing objective data to grasp formative principle and geometric characteristic of (this)distinct figures of Fractals. With this form of research, it is not so much about fractal in mathematics, but the concept of self-similarity and recursiveness, randomness, devices expressed from unspeakable space, and the formative similarity to graphic design are focused in this study. The fractal figures have characteristics in which the structure doesn't change the nature of things of the figure even in the process if repeated infinitely many times, the limit of the process produces is fractal. Almost all fractals are at least partially self-similar. This means that a part of the fractal is identical to the entire fractal itself even if there is an enlargement to infinitesimal. This means any part has all the information to recompose as whole. Based on this scene, the research is intended to examine possibility of analysis of fractals in geometric characteristics in plasticity toward forms in graphic design. As a result, a beautiful proportion appears in graphic design with calculation of mathematic. It should be an appropriate equation to express nature since the fractal dimension allows us to measure the complexity of an object and the Fractla geometry should pick out high addition in value of peculiarity and characteristics in the complex of art and science. At the stage where the necessity of accepting this demand and adapting ourselves to the change is gathering strength is very significant in this research.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.14 no.2
• /
• pp.172-176
• /
• 2010

Purpose: The patients' moves occurred at PET/CT scan will cause the decline of correctness in results by resulting in inconsistency of Attenuation Correction (AC) and effecting on quantitative evaluation. This study has evaluated the utility of reconstruction method using AC position changing method when having inconsistency of AC depending on the position change of emission scan after transmission scan in obtaining PET/CT 3D image. Materials and Methods: We created 1 mL syringe injection space up to ${\pm}2$, 6, 10 cm toward x and y axis based on central point of polystyrene ($20{\times}20110$ cm) into GE Discovery STE16 equipment. After projection of syringe with $^{18}F$-FDG 5 kBq/mL, made an emission by changing the position and obtained the image by using AC depending on the position change. Reconstruction method is an iteration reconstruction method and is applied two times of iteration and 20 of subset, and for every emission data, decay correction depending on time pass is applied. Also, after setting ROI to the position of syringe, compared %Difference (%D) at each position to radioactivity concentrations (kBq/mL) and central point. Results: Radioactivity concentrations of central point of emission scan is 2.30 kBq/mL and is indicated as 1.95, 1.82 and 1.75 kBq/mL, relatively for +x axis, as 2.07, 1.75 and 1.65 kBq/mL for -x axis, as 2.07, 1.87 and 1.90 kBq/mL for +y axis and as 2.17, 1.85 and 1.67 kBq/mL for -y axis. Also, %D is yield as 15, 20, 23% for +x axis, as 9, 23, 28% for -x axis, as 12, 21, 20% for +y axis and as 8, 22, 29% for -y axis. When using AC position changing method, it is indicated as 2.00, 1.95 and 1.80 kBq/mL, relatively for +x axis, as 2.25, 2.15 and 1.90 kBq/mL for -x axis, as 2.07, 1.90 and 1.90 kBq/mL for +y axis, and as 2.10, 2.02, and 1.72 kBq/mL for -y axis. Also, %D is yield as 13, 15, 21% for +x axis, as 2, 6, 17% for -x axis, as 9, 17, 17% for +y axis, and as 8, 12, 25% for -y axis. Conclusion: When in inconsistency of AC, radioactivity concentrations for using AC position changing method increased average of 0.14, 0.03 kBq/mL at x, y axis and %D was improved 6.1, 4.2%. Also, it is indicated that the more far from the central point and the further position from the central point under the features that spatial resolution is lowered, the higher in lowering of radioactivity concentrations. However, since in actual clinic, attenuation degree increases more, it is considered that when in inconsistency, such tolerance will be increased. Therefore, at the lesion of the part where AC is not inconsistent, the tolerance of radioactivity concentrations will be reduced by applying AC position changing method.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.7
• /
• pp.586-603
• /
• 2004

One of the subtle problems that make noise control difficult for engineers is “the invisibility of noise or sound.” The visual image of noise often helps to determine an appropriate means for noise control. There have been many attempts to fulfill this rather challenging objective. Theoretical or numerical means to visualize the sound field have been attempted and as a result, a great deal of progress has been accomplished, for example in the field of visualization of turbulent noise. However, most of the numerical methods are not quite ready to be applied practically to noise control issues. In the meantime, fast progress has made it possible instrumentally by using multiple microphones and fast signal processing systems, although these systems are not perfect but are useful. The state of the art system is recently available but still has many problematic issues : for example, how we can implement the visualized noise field. The constructed noise or sound picture always consists of bias and random errors, and consequently it is often difficult to determine the origin of the noise and the spatial shape of noise, as highlighted in the title. The first part of this paper introduces a brief history, which is associated with “sound visualization,” from Leonardo da Vinci's famous drawing on vortex street (Fig. 1) to modern acoustic holography and what has been accomplished by a line or surface array. The second part introduces the difficulties and the recent studies. These include de-Dopplerization and do-reverberation methods. The former is essential for visualizing a moving noise source, such as cars or trains. The latter relates to what produces noise in a room or closed space. Another mar issue associated this sound/noise visualization is whether or not Ivecan distinguish mutual dependence of noise in space : for example, we are asked to answer the question, “Can we see two birds singing or one bird with two beaks?"