• Journal of the Korean Association of Geographic Information Studies
• /
• v.5 no.1
• /
• pp.27-37
• /
• 2002

The classification accuracy of land cover has been considered as one of the major issues to estimate pollution loads generated from diffuse landuse patterns in a watershed. This research aimed to assess the effects of the acquisition methods and sampling size of training reference data on the classification accuracy of land cover using an imagery acquired by optical sensor(OPS) on JERS-1. Two kinds of data acquisition methods were considered to prepare training data. The first was to assign a certain land cover type to a specific pixel based on the researchers subjective discriminating capacity about current land use and the second was attributed to an aerial photograph incorporated with digital maps with GIS. Three different sizes of samples, 0.3%, 0.5%, and 1.0% of all pixels, were applied to examine the consistency of the classified land cover with the training data of corresponding pixels. Maximum likelihood scheme was applied to classify the land use patterns of JERS-1 imagery. Classification run applying an aerial photograph achieved 18 % higher consistency with the training data than the run applying the researchers subjective discriminating capacity. Regarding the sample size, it was proposed that the size of training area should be selected at least over 1% of all of the pixels in the study area in order to obtain the accuracy with 95% for JERS-1 satellite imagery on a typical small-to-medium-size urbanized area.

• Korean Journal of Remote Sensing
• /
• v.24 no.6
• /
• pp.605-612
• /
• 2008

In this study, we estimate solar surface insolation (SSI) by using physical methods with MTSAT-1R data. SSI is regarded as crucial parameter when interpreting solar-earth energy system, climate change, and agricultural production predict application. Most of SSI estimation model mainly uses ground based-measurement such as pyranometer to tune the constructed model and to validate retrieved SSI data from optical channels. When compared estimated SSI with pyranometer measurements, there are some systemic differences between those instruments. The pyranometer data observed upward-looking hemispherical solid angle and distributed hourly measurements data which are averaged every 2 minute instantaneous observation. Whereas MTSAT-1R channels data are taken instantaneously images at fixed measurement time over scan area, and are pixel-based observation with a much smaller solid angle view. Those temporal discrepancies result from systemic differences can induce validation error. In this study, we adjust hour when estimate SSI to improve the retrieved accurate SSI.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_3
• /
• pp.1965-1974
• /
• 2021

Satellite remote sensing approach can be actively used for forest monitoring. Especially, it is much meaningful to utilize Korea multi-purpose satellites, an independently operated satellite in Korea, for forest monitoring of Korea, Recently, several studies have been performed to exploit meaningful information from satellite remote sensed data via machine learning approaches. The forest information produced through machine learning approaches can be used to support the efficiency of traditional forest monitoring methods, such as in-situ survey or qualitative analysis of aerial image. The performance of machine learning approaches is greatly depending on the characteristics of study area and data. Thus, it is very important to survey the best model among the various machine learning models. In this study, the performance of deep neural network to classify artificial or natural forests was analyzed in Samcheok, Korea. As a result, the pixel accuracy was about 0.857. F1 scores for natural and artificial forests were about 0.917 and 0.433 respectively. The F1 score of artificial forest was low. However, we can find that the artificial and natural forest classification performance improvement of about 0.06 and 0.10 in F1 scores, compared to the results from single layered sigmoid artificial neural network. Based on these results, it is necessary to find a more appropriate model for the forest type classification by applying additional models based on a convolutional neural network.

• Investigative Magnetic Resonance Imaging
• /
• v.23 no.3
• /
• pp.251-258
• /
• 2019

Purpose: To assess the feasibility of the use of spin-echo echo-planar imaging (SE-EPI) magnetic resonance elastography (MRE) in livers of children and young adults. Materials and Methods: Patients (${\leq}20$ years old) who underwent 3T SE-EPI MRE were included retrospectively. Subjects were divided into three groups according to the purpose of the liver MRI: suspicion of fatty liver or focal fat deposition in the liver (FAT group), liver fibrosis after receiving a Kasai operation from biliary atresia (BA group), and hepatic iron deposition after receiving chemotherapy or transfusions (IRON group). Technical failure of MRE was defined when a stiffness map showed no pixel value with a confidence index higher than 95%, and the patients were divided as success and failure groups accordingly. Clinical findings including age, gender, weight, height, and body mass index and magnetic resonance imaging results including proton density fat fraction (PDFF), $T2^*$, and MRE values were assessed. Factors affecting failure of MRE were evaluated and the image quality in wave propagation image and stiffness map was evaluated using the appropriate scores. Results: Among total 240 patients (median 15 years, 211 patients in the FAT, 21 patients in the BA, and 8 patients in the IRON groups), technical failure was noted in six patients in the IRON group (6/8 patients, 75%), while there were no failures noted in the FAT and BA groups. These six patients had $T2^*$ values ranging from 0.9 to 3.8 ms. The image quality scores were not significantly different between the FAT and BA groups (P > 0.999), while the scores were significantly lower in the IRON group (P < 0.001). Conclusion: The 3T SE-EPI MRE in children and young adults had a high technical success rate. The technical failure was occurred in children with decreased $T2^*$ value (${\leq}3.8ms$) from iron deposition.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1663-1676
• /
• 2022

Recently, a number of deep-learning based land cover segmentation studies have been introduced. Some studies denoted that the performance of land cover segmentation deteriorated due to insufficient training data. In this study, we verified the improvement of land cover segmentation performance through data augmentation. U-Net was implemented for the segmentation model. And 2020 satellite-derived landcover dataset was utilized for the study data. The pixel accuracies were 0.905 and 0.923 for U-Net trained by original and augmented data respectively. And the mean F1 scores of those models were 0.720 and 0.775 respectively, indicating the better performance of data augmentation. In addition, F1 scores for building, road, paddy field, upland field, forest, and unclassified area class were 0.770, 0.568, 0.433, 0.455, 0.964, and 0.830 for the U-Net trained by original data. It is verified that data augmentation is effective in that the F1 scores of every class were improved to 0.838, 0.660, 0.791, 0.530, 0.969, and 0.860 respectively. Although, we applied data augmentation without considering class balances, we find that data augmentation can mitigate biased segmentation performance caused by data imbalance problems from the comparisons between the performances of two models. It is expected that this study would help to prove the importance and effectiveness of data augmentation in various image processing fields.

• Journal of the Korean Society of Radiology
• /
• v.17 no.1
• /
• pp.31-36
• /
• 2023

Among imaging and treatment devices for small animals, positron emission tomography(PET) causes a change in spatial resolution within a field of view. This is a phenomenon caused by using a small gantry and a thin and long scintillation pixel, and detectors that measure the interaction depth are being developed and researched to solve this problem. In this study, a detector that measures the interaction depth was designed using several scintillator blocks and light guides with different reflector patterns. The scintillator block composed of 4 × 4 arrays of 3 mm × 3 mm × 5 mm scintillation pixels formed four layers, and a light guide was inserted in each layer to configure the entire detector. In order to check whether the interaction depth was measured, a gamma ray interaction was generated at the center of all scintillation pixels to acquire data and then reconstructed into a flood image. The reflector patterns of the light guides inserted between the layers were all different, so the positions of the scintillation pixels for each layer were formed in different locations. It is considered that even spatial resolution can be achieved over all regions of the field of view if all positions of the scintillation pixels thus formed are separated and used for image reconstruction.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.19 no.1
• /
• pp.19-26
• /
• 2017

Surface air temperature ($T_{air}$) is a key variable for the meteorology and climatology, and is a fundamental factor of the terrestrial ecosystem functions. Satellite remote sensing from the Moderate Resolution Imaging Spectroradiometer (MODIS) provides an opportunity to monitor the $T_{air}$. However, the several problems such as frequent cloud cover and mountainous region can result in substantial retrieval error and signal loss in MODIS $T_{air}$. In this study, satellite-based $T_{air}$ was estimated under both clear and cloudy sky conditions in Gangwon Province using Aqua MODIS07 temperature profile product (MYD07_L2) and GCOM-W1 Advanced Microwave Scanning Radiometer 2 (AMSR2) brightness temperature ($T_b$) at 37 GHz frequency, and was compared with the measurements from the Automated Mountain Meteorology Stations (AMOS). The application of ambient temperature lapse rate was performed to improve the retrieval accuracy in mountainous region, which showed the improvement of estimation accuracy approximately 4% of RMSE. A simple pixel-wise regression method combining synergetic information from MYD07_L2 $T_{air}$ and AMSR2 $T_b$ was applied to estimate surface $T_{air}$ for all sky conditions. The $T_{air}$ retrievals showed favorable agreement in comparison with AMOS data (r=0.80, RMSE=7.9K), though the underestimation was appeared in winter season. Substantial $T_{air}$ retrievals were estimated 61.4% (n=2,657) for cloudy sky conditions. The results presented in this study indicate that the satellite remote sensing can produce the surface $T_{air}$ at the complex mountainous region for all sky conditions.

• Journal of the Korean Society of Radiology
• /
• v.79 no.5
• /
• pp.254-258
• /
• 2018

Purpose: Establishment of an appropriate protocol for breast magnetic resonance imaging (MRI) in the study of image quality standards to enhance the effectiveness of medical image information exchange, which is part of the construction and activation of clinical information exchange for healthcare informatization. Materials and Methods: The recommended protocols of breast and MRI scans were reviewed and the questionnaire was prepared by a responsible researcher. Then, a panel of 9 breast dedicated radiologists was set up in Korea. The expert panel conducted a total of three Delphi agreements to draw up a consensus on the breast MRI protocol. Results: The agreed breast MRI recommendation protocol is a 1.5 Tesla or higher device that acquires images with prone position using a breast dedicated coil and includes T2-weighted and pre-contrast T1-weighted images. Contrast enhancement images are acquired at least two times, and include 60-120 seconds between images and after 4 minutes. The contrast enhancement T1-weighted image should be less than 3 mm in thickness, less than 120 seconds in temporal resolution, and less than $1.5mm^2$ in-plane pixel resolution. Conclusion: The Delphi agreement of the domestic breast imaging specialist group has established the recommendation protocol of the effective breast MRI.

• Journal of KIISE:Software and Applications
• /
• v.30 no.5_6
• /
• pp.444-453
• /
• 2003

Recently, a great interest of bio-technology(BT) is concentrated and the image analysis technique for electrophoresis gels is highly requested to analyze genetic information or to look for some new bio-activation materials. For this purpose, the location and quantity of each band in a lane should be measured. In most of existing techniques, the approach of peak searching in a profile of a lane is used. But this peak is improper as the representative of a band, because its location does not correspond to that of the brightest pixel or the center of gravity. Also, it is improper to measure band quantity in most of these approaches because various enhancement processes are commonly applied to original images to extract peaks easily. In this paper, we adopt an approach to measure accumulated brightness as a band quantity in each band region, which Is extracted by not using any process of changing relative brightness, and the gravity center of the region is calculated as a band location. Actually, we first extract lanes with an entropy-based threshold calculated on a gel-image histogram. And then, three other methods are proposed and applied to extract bands. In the MER method, peaks and valleys are searched on a vertical search line by which each lane is bisected. And the minimum enclosing rectangle of each band is set between successive two valleys. On the other hand, in the RG-1 method, each band is extracted by using region growing with a peak as a seed, separating overlapped neighbor bands. In the RG-2 method, peaks and valleys are searched on two vertical lines by which each lane is trisected, and the left and right peaks nay be paired up if they seem to belong to the same band, and then each band region is grown up with a peak or both peaks if exist. To compare above three methods, we have measured the location and amount of bands. As a result, the average errors in band location of MER, RG-1, and RG-2 were 6%, 3%, and 1%, respectively, when the lane length is normalized to a unit value. And the average errors in band amount were 8%, 5%, and 2%, respectively, when the sum of band amount is normalized to a unit value. In conclusion, RG-2 was shown to be more reliable in the accuracy of measuring the location and amount of bands.

• Restorative Dentistry and Endodontics
• /
• v.35 no.3
• /
• pp.188-197
• /
• 2010

The purpose of this study was to compare radiopacity and radiographic discriminability of various FRC-Posts. Six FRC-Posts were investigated ; 1) FRC Postec Plus (Ivoclar Vivadent AG, Schaan, Liechtenstein), 2) Snowlight (Carbotech, Lewis center, OH, USA), 3) Dentin Post (Komet Brasseler, Lamgo, Germany), 4) Rely-X Fiber Post (3M ESPE, St.paul, MN, USA), 5) D.T.-Light Post (BISCO, Schaumburg, IL,USA), 6) Luxapost (DMG, Hamburg, Germany) The radiographs of each post with a reference 1 mm / 2 mm aluminum step-wedge was taken using digital sensor. The optical density were calculated by gray value of $10{\times}10$ pixel and compared in mm Al equivalent at five points. Six maxillary incisors of similar radiopacity were used. Radiographs of posts in Mx. incisors of lingual side of dry mandible were taken. We showed radiographs and asked the questionnaire to 3 radiologists, 3 endodontists, 3 general practitioners. The questionnaire was comprised of choices of the highest, lowest radiopaque individual post and the choices of best discriminable post at apical, coronal area. The following results were obtained. 1. Each post system showed various radiopacity. 2. There was change of discriminability between each post and simulated specimens regardless of examiner. Although each post showed various radiopacity, the difference of radiopacity did not affect on discriminability.