• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.1
• /
• pp.1-11
• /
• 2021

Detection of surface water features including river, wetland, reservoir from the satellite imagery can be utilized for sustainable management and survey of water resources. This research compared the water indices derived from the multispectral bands and the machine learning technique for detecting the surface water features from he Landsat-8 satellite image acquired in Daegu through the following steps. First, the NDWI(Normalized Difference Water Index) image and the MNDWI(Modified Normalized Difference Water Index) image were separately generated using the multispectral bands of the given Landsat-8 satellite image, and the two binary images were generated from these NDWI and MNDWI images, respectively. Then SVM(Support Vector Machine), the widely used machine learning techniques, were employed to generate the land cover image and the binary image was also generated from the generated land cover image. Finally the error matrices were used for measuring the accuracy of the three binary images for detecting the surface water features. The statistical results showed that the binary image generated from the MNDWI image(84%) had the relatively low accuracy than the binary image generated from the NDWI image(94%) and generated by SVM(96%). And some misclassification errors occurred in all three binary images where the land features were misclassified as the surface water features because of the shadow effects.

• The Journal of the Korea Contents Association
• /
• v.6 no.12
• /
• pp.1-11
• /
• 2006

Many research demonstrations and commercial applications have been tried to develop face detection and recognition systems. Human face detection plays an important role in applications such as access control and video surveillance, human computer interface, identity authentication, etc. There are some special problems such as a face connected with background, faces connected via the skin color, and a face divided into several small parts after skin region segmentation in generally. It can be allowed many face detection techniques to solve the first and second problems. However, it is not easy to detect a face divided into several parts of regions for reason of different illumination conditions in the third problem. Therefore, we propose an efficient modified skin segmentation algorithm to solve this problem because the typical region segmentation algorithm can not be used to. Our algorithm detects skin regions over the entire image, and then generates face candidate regions using our skin segmentation algorithm For each face candidate, we implement the procedure of region merging for divided regions in order to make a region using adjacency between homogeneous regions. We utilize various different searching window sizes to detect different size faces and a face detection classifier based on a back-propagation algorithm in order to verify whether the searching window contains a face or not.

• Journal of Korea Port Economic Association
• /
• v.26 no.1
• /
• pp.222-233
• /
• 2010

This paper aims at predicting the BDI from Jan. to Dec. 2010 using such econometric techniues of the univariate time series as stochastic ARIMA-type models and Hodrick-Prescott filtering technique. The multivariate cause-effect econometric model is not employed for not assuring a higher degree of forecasting accuracy than the univariate variable model. Such a cause-effect econometric model also fails in adjusting itself for the post-sample. This article introduces the two ARIMA models and five Intervention-ARIMA models. The monthly data cover the period January 2000 through December 2009. The out-of-sample forecasting performance is compared between the ARIMA-type models and the random walk model. Forecasting performance is measured by three summary statistics: root mean squared error (RMSE), mean absolute error (MAE) and mean error (ME). The RMSE and MAE indicate that the ARIMA-type models outperform the random walk model And the mean errors for all models are small in magnitude relative to the MAE's, indicating that all models don't have a tendency of overpredicting or underpredicting systematically in forecasting. The pessimistic ex-ante forecasts are expected to be 2,820 at the end of 2010 compared with the optimistic forecasts of 4,230.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.6
• /
• pp.117-125
• /
• 2008

The Object tracking by real-time image analysis is one of the major concerns in computer vision and its application fields. The Object detection process of real-time images must be preceded before the object tracking process. To achieve the stable object detection performance in the exterior environment, adaptive background model generation methods are needed. The adaptive background model can accept the nature's phenomena changes and adapt the system to the changes such as light or shadow movements that are caused by changes of meridian altitudes of the sun. In this paper, we propose a robust background model generation method effective in an illegal parking auto-detection application area. We also provide a evaluation method that judges whether a moving vehicle stops or not. As the first step, an initial background model is generated. Then the differences between the initial model and the input image frame is used to trace the movement of object. The moving vehicle can be easily recognized from the object tracking process. After that, the model is updated by the background information except the moving object. These steps are repeated. The experiment results show that our background model is effective and adaptable in the variable exterior environment. The results also show our model can detect objects moving slowly. This paper includes the performance evaluation results of the proposed method on the real roads.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.451-457
• /
• 2018

We propose an automatic detection and classification system of sewer damage database based on artificial intelligence and deep learning. In order to optimize the performance, we implemented a robust system against various environmental variations such as illumination and shadow changes. In our proposed system, a crack detection and damage classification method using a deep learning based Convolutional Neural Network (CNN) is implemented. For optimal results, 9,941 CCTV images with $256{\times}256$ pixel resolution were used for machine learning on the damaged area based on the CNN model. As a result, the recognition rate of 98.76% was obtained. Total of 646 images of $720{\times}480$ pixel resolution were extracted from various sewage DB for performance evaluation. Proposed system presents the optimal recognition rate for the automatic detection and classification of damage in the sewer DB constructed in various environments.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.36 no.1
• /
• pp.18-26
• /
• 2016

The semiconductor industry is one of the key industries of Korea, which has continued growing at a steady annual growth rate. Important technology for the semiconductor industry is high integration of devices. This is to increase the memory capacity for unit area, of which key is photolithography. The photolithography refers to a technique for printing the shadow of light lit on the mask surface on to wafer, which is the most important process in a semiconductor manufacturing process. In this study, the width and step-height of wafers patterned through this process were measured to ensure uniformity. The widths and inter-plate heights of the specimens patterned using photolithography were measured using transmissive digital holography. A transmissive digital holographic interferometer was configured, and nine arbitrary points were set on the specimens as measured points. The measurement of each point was compared with the measurements performed using a commercial device called scanning electron microscope (SEM) and Alpha Step. Transmission digital holography requires a short measurement time, which is an advantage compared to other techniques. Furthermore, it uses magnification lenses, allowing the flexibility of changing between high and low magnifications. The test results confirmed that transmissive digital holography is a useful technique for measuring patterns printed using photolithography.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.31 no.3
• /
• pp.61-74
• /
• 2013

This study examined and analyzed ancient writing and poetry regarding cases of appreciating plants by using pots in a garden of a palace or private houses by ancestors, and examined shape and planting method of plant species and potted plants, arrangement and preference of potted plants. As for the method of the study, description research method which examines and interprets poem and painting based on potted plants. The results of this study is summarized like the following. First, the plants which were favorably used for potted plants include 19 kinds such as Prunus mume, Pinus densiflora, Pinus pumila, Phyllostachys spp., Camellia japonica, Punica granatum, and Gardenia jasminoidesa, and as for herbs, 12 kinds such as Chrysanthemum monifolium and Nelumbo nusifera . Second, the species which were specially arranged into artificial shapes include Prunus mume and Pinus densiflora. The two plants made the shape of severe curves of stems such as Wangpi. Gyuban, and Bangan, and there are Pinus densiflora dwarfed potted plant whose roots are stretched on Prunus mume grafted into a strange stump and an oddly shaped stone. For the beauty of the dwarfed tree shape, pine cones are added to an old Pinus densiflora or Parthenocissus tricuspidata is planted to stems, and additional method of making moss on the soil, which is called 'Jongbunchuigyeong'. As for planting method, water culture, planting on a stone, planting on a charcoal, and assembled planting are expressed in poetry. Third, as for external space for potted plants, a place where a king stays, a bed room for a king, surrounding areas and gardens of private houses, and step stones were used as a space which adds artistic effects. Potted plants are placed on a table in a library, on a desk, on a drawer, and near a pillow as a small items in a room, and scholars enjoyed original characteristics and symbolism of the potted plants. Fourth, at the time of flowering of Prunus mume, poetry event was held to enjoy the tree and writing poetry begun. And at the time of flowering of Chrysanthemum monifolium, the flowers were floated in a liquor glass or shadow play was enjoyed. Fifth, potted plants played the role of garden ornaments in elegant events of a palace, the gentry, wedding ceremony, and sacrificial rites. Sixth, potted plants were used as tributes between countries, donation to a king, or a gift of a king. In addition, there were many cases where scholars exchanged potted plants and there is the first record of giving a potted plant in 'Mokeunsigo' by Mokeun Isaek, scholar in the late era of Goryeo. Seventh, at the time of flowering Prunus mume, Chrysanthemum monifolium, Gardenia jasminoides, Nelumbo nusifera, and Narcissustazetta var. chinensis, they enjoyed the particular fragrance and express it into poetry. Eighth, plant species from southern parts such as Camellia japonica, Daphne odora, Gardenia jasminoides, Citrus unshiu, Phyllostachys spp., Punica granatum, Rosa rugosa, and Musa basjoo, or foreign plant species, and species weak against the cold were utilized as pot plants for enjoying green trees indoors in northern central province in harshly cold winter.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.3
• /
• pp.199-208
• /
• 2019

As the number of available satellites increases and technology advances, image information outputs are becoming increasingly diverse and a large amount of data is accumulating. In this study, we propose a change detection method for high-resolution satellite images that uses transfer learning and a deep learning network to overcome the limit caused by insufficient training data via the use of pre-trained information. The deep learning network used in this study comprises convolutional layers to extract the spatial and spectral information and convolutional long-short term memory layers to analyze the time series information. To use the learned information, the two initial convolutional layers of the change detection network are designed to use learned values from 40,000 patches of the ISPRS (International Society for Photogrammertry and Remote Sensing) dataset as initial values. In addition, 2D (2-Dimensional) and 3D (3-dimensional) kernels were used to find the optimized structure for the high-resolution satellite images. The experimental results for the KOMPSAT-3A (KOrean Multi-Purpose SATllite-3A) satellite images show that this change detection method can effectively extract changed/unchanged pixels but is less sensitive to changes due to shadow and relief displacements. In addition, the change detection accuracy of two sites was improved by using 3D kernels. This is because a 3D kernel can consider not only the spatial information but also the spectral information. This study indicates that we can effectively detect changes in high-resolution satellite images using the constructed image information and deep learning network. In future work, a pre-trained change detection network will be applied to newly obtained images to extend the scope of the application.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.18 no.4
• /
• pp.233-241
• /
• 2016

Experiments were carried out to quantify the topographic effects on attenuation of sunshine in complex terrain and the results are expected to help convert the coarse resolution sunshine duration information provided by the Korea Meteorological Administration (KMA) into a detailed map reflecting the terrain characteristics of mountainous watershed. Hourly shaded relief images for one year, each pixel consisting of 0 to 255 brightness value, were constructed by applying techniques of shadow modeling and skyline analysis to the 3m resolution digital elevation model for an experimental watershed on the southern slope of Mt. Jiri in Korea. By using a bimetal sunshine recorder, sunshine duration was measured at three points with different terrain conditions in the watershed from May 15, 2015 to May 14, 2016. The brightness values of the 3 corresponding pixel points on the shaded relief map were extracted and regressed to the measured sunshine duration, resulting in a brightness-sunshine duration response curve for a clear day. We devised a method to calibrate this curve equation according to sky condition categorized by cloud amount and used it to derive an empirical model for estimating sunshine duration over a complex terrain. When the performance of this model was compared with a conventional scheme for estimating sunshine duration over a horizontal plane, the estimation bias was improved remarkably and the root mean square error for daily sunshine hour was 1.7hr, which is a reduction by 37% from the conventional method. In order to apply this model to a given area, the clear-sky sunshine duration of each pixel should be produced on hourly intervals first, by driving the curve equation with the hourly shaded relief image of the area. Next, the cloud effect is corrected by 3-hourly 'sky condition' of the KMA digital forecast products. Finally, daily sunshine hour can be obtained by accumulating the hourly sunshine duration. A detailed sunshine duration distribution of 3m horizontal resolution was obtained by applying this procedure to the experimental watershed.