• Korean Journal of Remote Sensing
• /
• v.36 no.2_1
• /
• pp.199-215
• /
• 2020

A seagrass that is marine vascular plants plays an important role in the marine ecosystem, so periodic monitoring ofseagrass habitatsis being performed. Recently, the use of dronesthat can easily acquire very high-resolution imagery is increasing to efficiently monitor seagrass habitats. And deep learning based on a convolutional neural network has shown excellent performance in semantic segmentation. So, studies applied to deep learning models have been actively conducted in remote sensing. However, the segmentation accuracy was different due to the hyperparameter, various deep learning models and imagery. And the normalization of the image and the tile and batch size are also not standardized. So,seagrass habitats were segmented from drone-borne imagery using a deep learning that shows excellent performance in this study. And it compared and analyzed the results focused on normalization and tile size. For comparison of the results according to the normalization, tile and batch size, a grayscale image and grayscale imagery converted to Z-score and Min-Max normalization methods were used. And the tile size isincreased at a specific interval while the batch size is allowed the memory size to be used as much as possible. As a result, IoU was 0.26 ~ 0.4 higher than that of Z-score normalized imagery than other imagery. Also, it wasfound that the difference to 0.09 depending on the tile and batch size. The results were different according to the normalization, tile and batch. Therefore, this experiment found that these factors should have a suitable decision process.

• Clean Technology
• /
• v.28 no.4
• /
• pp.323-330
• /
• 2022

Microfluidic paper-based analytical devices (μPADs) have recently been in the spotlight for their applicability in point-of-care diagnostics and environmental material detection. This study presents a double-sided printing method for fabricating 3D-μPADs, providing simple and cost effective metal ion detection. The design of the 3D-μPAD was made into an acryl stamp by laser cutting and then coating it with a thin layer of PDMS using the spin-coating method. This fabricated stamp was used to form the 3D structure of the hydrophobic barrier through a double-sided contact printing method. The fabrication of the 3D hydrophobic barrier within a single sheet was optimized by controlling the spin-coating rate, reagent ratio and contacting time. The optimal conditions were found by analyzing the area change of the PDMS hydrophobic barrier and hydrophilic channel using ink with chromatography paper. Using the fabricated 3D-μPAD under optimized conditions, Ni²⁺, Cu²⁺, Hg²⁺, and pH were detected at different concentrations and displayed with color intensity in grayscale for quantitative analysis using ImageJ. This study demonstrated that a 3D-μPAD biosensor can be applied to detect metal ions without special analysis equipment. This 3D-μPAD provides a highly portable and rapid on-site monitoring platform for detecting multiple heavy metal ions with extremely high repeatability, which is useful for resource-limited areas and developing countries.

• Journal of Internet Computing and Services
• /
• v.16 no.2
• /
• pp.49-55
• /
• 2015

According to the statistics of traffic accidents over recent 5 years, traffic accidents during the night times happened more than the day times. There are various causes to occur traffic accidents and the one of the major causes is inappropriate or missing street lights that make driver's sight confused and causes the traffic accidents. In this paper, with smartphones, we designed and implemented a lane luminance measurement application which stores the information of driver's location, driving, and lane luminance into database in real time to figure out the inappropriate street light facilities and the area that does not have any street lights. This application is implemented under Native C/C++ environment using android NDK and it improves the operation speed than code written in Java or other languages. To measure the luminance of road, the input image with RGB color space is converted to image with YCbCr color space and Y value returns the luminance of road. The application detects the road lane and calculates the road lane luminance into the database sever. Also this application receives the road video image using smart phone's camera and improves the computational cost by allocating the ROI(Region of interest) of input images. The ROI of image is converted to Grayscale image and then applied the canny edge detector to extract the outline of lanes. After that, we applied hough line transform method to achieve the candidated lane group. The both sides of lane is selected by lane detection algorithm that utilizes the gradient of candidated lanes. When the both lanes of road are detected, we set up a triangle area with a height 20 pixels down from intersection of lanes and the luminance of road is estimated from this triangle area. Y value is calculated from the extracted each R, G, B value of pixels in the triangle. The average Y value of pixels is ranged between from 0 to 100 value to inform a luminance of road and each pixel values are represented with color between black and green. We store car location using smartphone's GPS sensor into the database server after analyzing the road lane video image with luminance of road about 60 meters ahead by wireless communication every 10 minutes. We expect that those collected road luminance information can warn drivers about safe driving or effectively improve the renovation plans of road luminance management.

• Journal of Korea Multimedia Society
• /
• v.23 no.5
• /
• pp.650-657
• /
• 2020

The rapid growth of internet users and faster network speed are driving the new ICT services. ICT Technology has improved our way of thinking and style of life, but it has created security problems such as malware, ransomware, and so on. Therefore, we should research against the increase of malware and the emergence of malicious code. For this, it is necessary to accurately and quickly detect and classify malware family. In this paper, we analyzed and classified visualization technology, which is a preprocessing technology used for deep learning-based malware classification. The first method is to convert each byte into one pixel of the image to produce a grayscale image. The second method is to convert 2bytes of the binary to create a pair of coordinates. The third method is the method using LSH. We proposed improving the technique of using the entire existing malicious code file for visualization, extracting only the areas where important information is expected to exist and then visualizing it. As a result of experimenting in the method we proposed, it shows that selecting and visualizing important information and then classifying it, rather than containing all the information in malicious code, can produce better learning results.

• Korean Journal of Remote Sensing
• /
• v.32 no.6
• /
• pp.693-701
• /
• 2016

To make a mosaicked image, we need to estimate the geometric relationship between individual images. For such estimation, we needs tiepoint information. In general, feature-based methods are used to extract tiepoints. However, in the case of textureless images, feature-based methods are hardly applicable. In this paper, we propose a frequency domain matching method for automated mosaicking of textureless images. There are three steps in the proposed method. The first step is to convert color images to grayscale images, remove noise, and extract edges. The second step is to define a Region Of Interest (ROI). The third step is to perform phase correlation between two images and select the point with best correlation as tiepoints. For experiments, we used GOCI image slots and general frame camera images. After the three steps, we produced reliable tiepoints from textureless as well as textured images. We have proved application possibility of the proposed method.

• Journal of Broadcast Engineering
• /
• v.15 no.1
• /
• pp.133-143
• /
• 2010

This paper proposes a quadtree image compression method which encodes images efficiently and also makes unartificial compressed images. The proposed compression method uses edge-based quadtree decomposition to preserve the significant edge-lines, and it utilizes the predictive coding scheme to exploit the high correlation of the leaf node blocks. The simulation results with $256\times256$ grayscale images verify that the proposed method yields better coding efficiency than the JPEG by about 25 percents. The proposed method can provide more natural compressed images as it is free from the ringing effect in the compressed images which used to be in the images compressed by the fixed block based encoders such as the JPEG.

• Journal of KIISE:Software and Applications
• /
• v.31 no.2
• /
• pp.203-212
• /
• 2004

The watermarking is a method to achieve the copyright protection of multimedia contents. Among several media, the left documents show very peculiar properties: block/line/word patterning, clear separation between foreground and background areas. So algorithms specific to the text documents are required that meet those properties. This paper proposes a novel watermarking algorithm for the grayscale text document images. The algorithm inserts the watermark signals through the edge direction histograms. A concept of sub-image consistency is developed that the sub-images have similar shapes in terms of edge direction histograms. Using Korean, Chinese, and English document images, the concept is evaluated and proven to be valid over a wide range of document images. To insert watermark signals, the edge direction histogram is modified slightly. The experiments were performed on various document images and the algorithm was evaluated in terms of imperceptibility and robustness.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.136-136
• /
• 2021

In this study, a deep convolutional neural network (DCNN) model is proposed for short-term precipitation forecasting using weather radar-based images. The DCNN model is a combination of convolutional neural networks, autoencoder neural networks, and U-net architecture. The weather radar-based image data used here are retrieved from competition for rainfall forecasting in Korea (AI Contest for Rainfall Prediction of Hydroelectric Dam Using Public Data), organized by Dacon under the sponsorship of the Korean Water Resources Association in October 2020. This data is collected from rainy events during the rainy season (April - October) from 2010 to 2017. These images have undergone a preprocessing step to convert from weather radar data to grayscale image data before they are exploited for the competition. Accordingly, each of these gray images covers a spatial dimension of 120×120 pixels and has a corresponding temporal resolution of 10 minutes. Here, each pixel corresponds to a grid of size 4km×4km. The DCNN model is designed in this study to provide 10-minute predictive images in advance. Then, precipitation information can be obtained from these forecast images through empirical conversion formulas. Model performance is assessed by comparing the Score index, which is defined based on the ratio of MAE (mean absolute error) to CSI (critical success index) values. The competition results have demonstrated the impressive performance of the DCNN model, where the Score value is 0.530 compared to the best value from the competition of 0.500, ranking 16^th out of 463 participating teams. This study's findings exhibit the potential of applying the DCNN model to short-term rainfall prediction using weather radar-based images. As a result, this model can be applied to other areas with different spatiotemporal resolutions.

• The Journal of Korea Robotics Society
• /
• v.12 no.3
• /
• pp.313-321
• /
• 2017

One of the most frequently performed tasks in human-robot interaction (HRI), intelligent vehicles, and security systems is face related applications such as face recognition, facial expression recognition, driver state monitoring, and gaze estimation. In these applications, accurate head pose estimation is an important issue. However, conventional methods have been lacking in accuracy, robustness or processing speed in practical use. In this paper, we propose a novel method for estimating head pose with a monocular camera. The proposed algorithm is based on a deep neural network for multi-task learning using a small grayscale image. This network jointly detects multi-view faces and estimates head pose in hard environmental conditions such as illumination change and large pose change. The proposed framework quantitatively and qualitatively outperforms the state-of-the-art method with an average head pose mean error of less than $4.5^{\circ}$ in real-time.

• Journal of Biomedical Engineering Research
• /
• v.28 no.2
• /
• pp.174-177
• /
• 2007

Trabecular bone can be accurately represented using image-based finite element modeling and analysis of these bone models is widely used to predict their mechanical properties. However, the choice of thresholding technique, a necessary step in converting grayscale images to finite element models which can thus significantly influence the structure of the resulting finite element model, is often overlooked. Therefore, we investigated the effects of thresholding techniques on micro-computed tomography (micro-CT) based finite element models of trabecular bone. Three types of thresholding techniques were applied to micro-CT images of trabecular bone which resulted in three unique finite element models for each specimen. Bone volume fractions and apparent moduli were predicted for each model and compared to experimental results. Our findings suggest that predictions of apparent properties agree well with experimental measurements regardless of the choice of thresholding technique in micro CT images of trabecular bone.