• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.4
• /
• pp.325-331
• /
• 2015

This paper suggests an intersection method to improve the accuracy of three-dimensional position from heterogeneous satellite stereo images, and addresses validation of the suggested method following the experimental results. The three-dimensional position is achieved by determining an intersection point of two rays that have been precisely adjusted through the sensor orientation. In case of conventional homogeneous satellite stereo images, the intersection point is generally determined as a mid-point of the shortest line that links two rays in at least square fashion. In this paper, a refined method, which determines the intersection point upon the ray adjusted at the higher resolution image, was used to improve the positioning accuracy of heterogeneous satellite images. Those heterogeneous satellite stereo pairs were constituted using two KOMPSAT-2 and QuickBird images of covering the same area. Also, the positioning results were visually compared in between the conventional intersection and the refined intersection, while the quantitative analysis was performed. The results demonstrated that the potential of refined intersection improved the positioning accuracy of heterogeneous satellite stereo pairs; especially, with a weak geometry of the heterogeneous satellite stereo, the greater effects on the accuracy improvement.

• Journal of KIISE:Databases
• /
• v.37 no.4
• /
• pp.177-184
• /
• 2010

In these day, many data including sensor, delivery, credit and stock data are generated continuously in massive quantity. It is difficult to learn from these data because they are large in volume and changing fast in their concepts. To handle these problems, learning methods based in sliding window methods over time have been used. But these approaches have a problem of rebuilding models every time new data arrive, which requires a lot of time and cost. Therefore we need very simple incremental learning methods. Bayesian method is an example of these methods but it has a disadvantage which it requries the prior knowledge(probabiltiy) of data. In this study, we propose a learning method based on attribute values. In the proposed method, even though we don't know the prior knowledge(probability) of data, we can apply our new method to data. The main concept of this method is that each attribute value is regarded as an expert learner, summing up the expert learners lead to better results. Experimental results show our learning method learns from data very fast and performs well when compared to current learning methods(decision tree and bayesian).

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.10
• /
• pp.447-454
• /
• 2015

This paper proposes geographical name denoising by machine learning of event detection based on twitter. Recently, the increasing number of smart phone users are leading the growing user of SNS. Especially, the functions of short message (less than 140 words) and follow service make twitter has the power of conveying and diffusing the information more quickly. These characteristics and mobile optimised feature make twitter has fast information conveying speed, which can play a role of conveying disasters or events. Related research used the individuals of twitter user as the sensor of event detection to detect events that occur in reality. This research employed geographical name as the keyword by using the characteristic that an event occurs in a specific place. However, it ignored the denoising of relationship between geographical name and homograph, it became an important factor to lower the accuracy of event detection. In this paper, we used removing and forecasting, these two method to applied denoising technique. First after processing the filtering step by using noise related database building, we have determined the existence of geographical name by using the Naive Bayesian classification. Finally by using the experimental data, we earned the probability value of machine learning. On the basis of forecast technique which is proposed in this paper, the reliability of the need for denoising technique has turned out to be 89.6%.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.1
• /
• pp.48-63
• /
• 2015

In this study, we introduce various hyperspectral data processing techniques for the monitoring of shallow and coastal waters to enlarge the application range and to improve the accuracy of the end results in Korea. Unlike land, more accurate atmospheric correction is needed in coastal region showing relatively low reflectance in visible wavelengths. Sun-glint which occurs due to a geometry of sun-sea surface-sensor is another issue for the data processing in the ocean application of hyperspectal imagery. After the preprocessing of the hyperspectral data, a semi-analytical algorithm based on a radiative transfer model and a spectral library can be used for bathymetry mapping in coastal area, type classification and status monitoring of benthos or substrate classification. In general, semi-analytical algorithms using spectral information obtained from hyperspectral imagey shows higher accuracy than an empirical method using multispectral data. The water depth and quality are constraint factors in the ocean application of optical data. Although a radiative transfer model suggests the theoretical limit of about 25m in depth for bathymetry and bottom classification, hyperspectral data have been used practically at depths of up to 10 m in shallow and coastal waters. It means we have to focus on the maximum depth of water and water quality conditions that affect the coastal applicability of hyperspectral data, and to define the spectral library of coastal waters to classify the types of benthos and substrates.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1517-1526
• /
• 2021

With the recent global and domestic development of Earth observation satellites, the applications of satellite images have been widened. Research for improving the geometric accuracy of satellite images is being actively carried out. This paper studies the possibility of automated ground control point (GCP) generation for CAS-4 satellite, to be launched in 2025 with the capability of image acquisition at 5 m ground sampling distance (GSD). In particular, this paper focuses to check whether GCP chips with 25 cm GSD established for CAS-1 satellite images can be used for CAS-4 and to check whether optimalspatial resolution for matching between CAS-4 images and GCP chips can be determined to improve matching performance. Experiments were carried out using RapidEye images, which have similar GSD to CAS-4. Original satellite images were upsampled to make satellite images with smaller GSDs. At each GSD level, up-sampled satellite images were matched against GCP chips and precision sensor models were estimated. Results shows that the accuracy of sensor models were improved with images atsmaller GSD compared to the sensor model accuracy established with original images. At 1.25~1.67 m GSD, the accuracy of about 2.4 m was achieved. This finding lead that the possibility of automated GCP extraction and precision ortho-image generation for CAS-4 with improved accuracy.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.4
• /
• pp.235-243
• /
• 2021

River surveying is conducted to acquire basic geographic data for river master plans and various river maintenance, and it is also used to predict changes after river maintenance construction. ABL (Airborne Bathymetric LiDAR) system is a cutting-edge surveying technology that can simultaneously observe the water surface and river bed using a green laser, and has many advantages in river surveying. In order to use the ABL data for river surveying, it is prerequisite step to segment and extract the water surface and river bed points from the original point cloud data. In this study, point cloud segmentation was performed by applying the ground filtering technique, ATIN (Adaptive Triangular Irregular Network) to the ABL data and then, the water surface and riverbed point clouds were extracted sequentially. In the Gokgyocheon river area, Chungcheongnam-do, the experiment was conducted with the dataset obtained using the Leica Chiroptera 4X sensor. As a result of the study, the overall classification accuracy for the water surface and riverbed was 88.8%, and the Kappa coefficient was 0.825, confirming that the ABL data can be effectively used for river surveying.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.57-65
• /
• 2021

We propose a novel method to detect abnormal data of specific symptoms using deep learning in air pollution measurement system. Existing methods generally detect abnomal data by classifying data showing unusual patterns different from the existing time series data. However, these approaches have limitations in detecting specific symptoms. In this paper, we use DeepLab V3+ model mainly used for foreground segmentation of images, whose structure has been changed to handle one-dimensional data. Instead of images, the model receives time-series data from multiple sensors and can detect data showing specific symptoms. In addition, we improve model's performance by reducing the complexity of noisy form time series data by using 'piecewise aggregation approximation'. Through the experimental results, it can be confirmed that anomaly data detection can be performed successfully.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.403-412
• /
• 2021

Despite strengthening requirements for fire retardancy and applied buildings of insulation panels, the number of fires and influence of damage have increased. In this study, the thermal effects were evaluated as the separation distances, and three types of EPS panel, glass wool panel, and gypsum board panel were then selected. Temperature sensors on the panels were installed vertically from the ground. The fire source on the lamination layer of lumber was ignited by changes in the separation distances (0 cm, 25 cm, 50 cm) from the panels. The test results suggested that the maximum temperature was 349 ℃ in the EPS panel. The inside/outside shape changes were limited by the height of the low and middle positions until the critical point of a 25 cm separation distance. Furthermore, the combustion marks appeared after 500 s on average, and then the EPS panel with a high fire strength showed a broad "U type" pattern, glass wool panel, and gypsum board panel showed medium or narrow "V type" pattern. Therefore, the acquired data can provide valuable information for evaluating the fire risks and verifying fire investigation from buildings composed of these insulation panels.

• 재활복지
• /
• v.21 no.3
• /
• pp.129-146
• /
• 2017

In an event of an emergency, such as fire in a building, visually impaired and blind people are prone to exposed to a level of danger that is greater than that of normal people, for they cannot be aware of it quickly. Current fire detection methods such as smoke detector is very slow and unreliable because it usually uses chemical sensor based technology to detect fire particles. But by using vision sensor instead, fire can be proven to be detected much faster as we show in our experiments. Previous studies have applied various image processing and machine learning techniques to detect fire, but they usually don't work very well because these techniques require hand-crafted features that do not generalize well to various scenarios. But with the help of recent advancement in the field of deep learning, this research can be conducted to help solve this problem by using deep learning-based object detector that can detect fire using images from security camera. Deep learning based approach can learn features automatically so they can usually generalize well to various scenes. In order to ensure maximum capacity, we applied the latest technologies in the field of computer vision such as YOLO detector in order to solve this task. Considering the trade-off between recall vs. complexity, we introduced two convolutional neural networks with slightly different model's complexity to detect fire at different recall rate. Both models can detect fire at 99% average precision, but one model has 76% recall at 30 FPS while another has 61% recall at 50 FPS. We also compare our model memory consumption with each other and show our models robustness by testing on various real-world scenarios.

• Ecology and Resilient Infrastructure
• /
• v.5 no.4
• /
• pp.257-263
• /
• 2018

This study is to develop a GSTM (Green infrastructure Surface Temperature Measurment) equipment for reducing the surface temperature of GI by using LID Method. The tests were conducted including GI products such as Greening block, Pervious Block, Soil Block and so on. The GSTM equipment developed by considering the literature surveys are characterized as follows. The non-contact infrared temperature sensor was used to measure the surface temperature, and it was improved to measure the overall average temperature including the center and the corner temperature of the specimen. The developed GSTM equipment was used to compare performance of asphalt and GI products. As a result, the Greening Block show a high difference of $18.4^{\circ}C$ and it contributes to the decrease of surface temperature.