• 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 Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.1-9
• /
• 2022

In this paper, we propose a vector-based augmentation technique that can generate data required for crack detection and a ConvNet(Convolutional Neural Network) technique that can learn it. Detecting cracks quickly and accurately is an important technology to prevent building collapse and fall accidents in advance. In order to solve this problem with artificial intelligence, it is essential to obtain a large amount of data, but it is difficult to obtain a large amount of crack data because the situation for obtaining an actual crack image is mostly dangerous. This problem of database construction can be alleviated with elastic distortion, which increases the amount of data by applying deformation to a specific artificial part. In this paper, the improved crack pattern results are modeled using ConvNet. Rather than elastic distortion, our method can obtain results similar to the actual crack pattern. By designing the crack data augmentation based on a vector, rather than the pixel unit used in general data augmentation, excellent results can be obtained in terms of the amount of crack change. As a result, in this paper, even though a small number of crack data were used as input, a crack database can be efficiently constructed by generating various crack directions and patterns.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1210-1210
• /
• 2001

On farm analysis of protein, moisture and oil in cereals and oil seeds is quickly being adopted by Australian farmers. The benefits of being able to measure protein and oil in grains and oil seeds are several : $\square$ Optimize crop payments $\square$ Monitor effects of fertilization $\square$ Blend on farm to meet market requirements $\square$ Off farm marketing - sell crop with load by load analysis However farmers are not NIR spectroscopists and the process of calibrating instruments has to the duty of the supplier. With the potential number of On Farm analyser being in the thousands, then the task of calibrating each instrument would be impossible, let alone the problems encountered with updating calibrations from season to season. As such, NIR technology Australia has developed a mechanism for \ulcorner\ulcorner\ulcorner their range of Cropscan 2000G NIR analysers so that a single calibration can be transferred from the master instrument to every slave instrument. Whole grain analysis has been developed over the last 10 years using Near Infrared Transmission through a sample of grain with a pathlength varying from 5-30mm. A continuous spectrum from 800-1100nm is the optimal wavelength coverage fro these applications and a grating based spectrophotometer has proven to provide the best means of producing this spectrum. The most important aspect of standardizing NIB instruments is to duplicate the spectral information. The task is to align spectrum from the slave instruments to the master instrument in terms of wavelength positioning and then to adjust the spectral response at each wavelength in order that the slave instruments mimic the master instrument. The Cropscan 2000G and 2000B Whole Grain Analyser use flat field spectrographs to produce a spectrum from 720-1100nm and a silicon photodiode array detector to collect the spectrum at approximately 10nm intervals. The concave holographic gratings used in the flat field spectrographs are produced by a process of photo lithography. As such each grating is an exact replica of the original. To align wavelengths in these instruments, NIR wheat sample scanned on the master and the slave instruments provides three check points in the spectrum to make a more exact alignment. Once the wavelengths are matched then many samples of wheat, approximately 10, exhibiting absorbances from 2 to 4.5 Abu, are scanned on the master and then on each slave. Using a simple linear regression technique, a slope and bias adjustment is made for each pixel of the detector. This process corrects the spectral response at each wavelength so that the slave instruments produce the same spectra as the master instrument. It is important to use as broad a range of absorbances in the samples so that a good slope and bias estimate can be calculated. These Slope and Bias (S'||'&'||'B) factors are then downloaded into the slave instruments. Calibrations developed on the master instrument can then be downloaded onto the slave instruments and perform similarly to the master instrument. The data shown in this paper illustrates the process of calculating these S'||'&'||'B factors and the transfer of calibrations for wheat, barley and sorghum between several instruments.

• Journal of Advanced Navigation Technology
• /
• v.27 no.3
• /
• pp.306-313
• /
• 2023

Realistic and graphics-based virtual reality content is based on 360-degree videos, and viewport extraction through the viewer's intention or automatic recommendation function is essential. This paper designs a viewport extraction system based on multiple object tracking in 360-degree videos and proposes a parallel computing structure necessary for multiple viewport extraction. The viewport extraction process in 360-degree videos is parallelized by composing pixel-wise threads, through 3D spherical surface coordinate transformation from ERP coordinates and 2D coordinate transformation of 3D spherical surface coordinates within the viewport. The proposed structure evaluated the computation time for up to 30 viewport extraction processes in aerial 360-degree video sequences and confirmed up to 5240 times acceleration compared to the CPU-based computation time proportional to the number of viewports. When using high-speed I/O or memory buffers that can reduce ERP frame I/O time, viewport extraction time can be further accelerated by 7.82 times. The proposed parallelized viewport extraction structure can be applied to simultaneous multi-access services for 360-degree videos or virtual reality contents and video summarization services for individual users.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.125-137
• /
• 2021

The number of CCTV installed in Korea is over 1.3 million, increasing by more than 15% annually. However, due to the limited budget compared to the installation demand, the infrastructure is composed of 500,000 pixel low-quality CCTV, and there is a limits on identification of objects in the video. Public CCTV has high utility in various fields such as crime prevention, traffic information collection (control), facility management, and fire prevention. Especially, since installed in high height, it works as its role in solving diverse crime and is in increasing trend. However, the current public CCTV field is operated with potential problems such as inability to identify due to environmental factors such as fog, snow, and rain, and the low-quality of collected images due to the installation of low-quality CCTV. Therefore, in this study, in order to remove the typical low-quality elements of public CCTV, the method of attenuating scattered light in the image caused by dust, water droplets, fog, etc and algorithm application method which uses deep-learning algorithm to improve input video into videos over quality over 4K are suggested.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4D
• /
• pp.687-693
• /
• 2006

Image co-registration is the process of overlaying two images of the same scene, one of which represents a reference image, while the other is geometrically transformed to the one. In order to improve efficiency and effectiveness of the co-registration approach, the author proposed a pre-qualified area matching algorithm which is composed of feature extraction with canny operator and area matching algorithm with cross correlation coefficient. For refining matching points, outlier detection using studentized residual was used and iteratively removes outliers at the level of three standard deviation. Throughout the pre-qualification and the refining processes, the computation time was significantly improved and the registration accuracy is enhanced. A prototype of the proposed algorithm was implemented and the performance test of 3 Landsat images of Korea. showed: (1) average RMSE error of the approach was 0.435 pixel; (2) the average number of matching points was over 25,573; (3) the average processing time was 4.2 min per image with a regular workstation equipped with a 3 GHz Intel Pentium 4 CPU and 1 Gbytes Ram. The proposed approach achieved robustness, full automation, and time efficiency.

• Progress in Medical Physics
• /
• v.18 no.2
• /
• pp.81-86
• /
• 2007

The cone-beam CT (CBCT) which is acquired using on-board imager (OBI) attached to a linear accelerator is widely used for the image guided radiation therapy. In this study, the effect of respiratory motion on the quality of CBCT image was evaluated. A phantom system was constructed in order to simulate respiratory motion. One part of the system is composed of a moving plate and a motor driving component which can control the motional cycle and motional range. The other part is solid water phantom containing a small cubic phantom ($2{\times}2{\times}2cm^3$) surrounded by air which simulate a small tumor volume in the lung air cavity CBCT images of the phantom were acquired in 20 different cases and compared with the image in the static status. The 20 different cases are constituted with 4 different motional ranges (0.7 cm, 1.6 cm, 2.4 cm, 3.1 cm) and 5 different motional cycles (2, 3, 4, 5, 6 sec). The difference of CT number in the coronal image was evaluated as a deformation degree of image quality. The relative average pixel intensity values as a compared CT number of static CBCT image were 71.07% at 0.7 cm motional range, 48.88% at 1.6 cm motional range, 30.60% at 2.4 cm motional range, 17.38% at 3.1 cm motional range The tumor phantom sizes which were defined as the length with different CT number compared with air were increased as the increase of motional range (2.1 cm: no motion, 2.66 cm: 0.7 cm motion, 3.06 cm: 1.6 cm motion, 3.62 cm: 2.4 cm motion, 4.04 cm: 3.1 cm motion). This study shows that respiratory motion in the region of inhomogeneous structures can degrade the image quality of CBCT and it must be considered in the process of setup error correction using CBCT images.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.17 no.1
• /
• pp.80-90
• /
• 2014

The objective of this research is to estimate the stand volume of Pinus koraiensis, by using the investigated volume and the information of remote sensing(RS), in the research forest of Kangwon National University. The average volume of the research forest per hectare was $307.7m^3/ha$ and standard deviation was $168.4m^3/ha$. Before and after carrying out 3 by 3 majority filtering on TM image, eleven indices were extracted each time. Independent variables needed for linear regression equation were selected using mean pixel values by indices. The number of indices were eleven: six Bands(except for thermal Band), NDVI, Band Ratio(BR1:Band4/Band3, BR2:Band5/Band4, BR3:Band7/Band4), Tasseled Cap-Greeness. As a result, NDVI and TC G were chosen as the most suitable indices for regression before and after filtering, and R-squared was high: 0.736 before filtering, 0.753 after filtering. As a result of error verification for an exact comparison, RMSE before and after filtering was about $69.1m^3/ha$, $67.5m^3/ha$, respectively, and bias was $-12.8m^3/ha$, $9.7m^3/ha$, respectively. Therefore, the regression conducted with filtering was selected as an appropriate model because of low RMSE and bias. The estimated stand volume applying the regression was $160,758m^3$, and the average volume was $314m^3/ha$. This estimation was 1.2 times higher than the actual stand volume of Pinus koraiensis.

• Korean Journal of Remote Sensing
• /
• v.30 no.1
• /
• pp.109-126
• /
• 2014

We improved the Land Surface Emissivity (LSE) data (Kongju National University LSE v.2: KNULSE_v2) over the Communication, Ocean and Meteorological Satellite (COMS) observation region using recent(2009-2012) Moderate Resolution Imaging Spectroradiometer (MODIS) data. The surface emissivity was derived using the Vegetation Cover Method (VCM) based on the assumption that the pixel is only composed of ground and vegetation. The main issues addressed in this study are as follows: 1) the impacts of snow cover are included using Normalized Difference Snow Index (NDSI) data, 2) the number of channels is extended from two (11, 12 ${\mu}m$) to four channels (3.7, 8.7, 11, 12 ${\mu}m$), 3) the land cover map data is also updated using the optimized remapping of the five state-of-the-art land cover maps, and 4) the latest look-up table for the emissivity of land surface according to the land cover is used. The updated emissivity data showed a strong seasonal variation with high and low values for the summer and winter, respectively. However, the surface emissivity over the desert or evergreen tree areas showed a relatively weak seasonal variation irrespective of the channels. The snow cover generally increases the emissivity of 3.7, 8.7, and 11 ${\mu}m$ but decreases that of 12 ${\mu}m$. As the results show, the pattern correlation between the updated emissivity data and the MODIS LSE data is clearly increased for the winter season, in particular, the 11 ${\mu}m$. However, the differences between the two emissivity data are slightly increased with a maximum increase in the 3.7 ${\mu}m$. The emissivity data updated in this study can be used for the improvement of accuracy of land surface temperature derived from the infrared channel data of COMS.

• The Korean Journal of Nuclear Medicine
• /
• v.36 no.5
• /
• pp.306-313
• /
• 2002

Purpose: Diuretic renography (DR) can be false negative in patients with upper urinary tract obstruction due to low compliance of the renal pelvis. Delayed parenchymal transit (DPT) may be a valuable sign in case of false negative DR. We compared the diagnostic values of DR and DPT during Tc-99m MAG3 diuretic scan in adults with suspected unilateral obstructive uropathy. Materials and Methods: Fifty-four patients(male:female=30:24, age: $40.7{\pm}15.5$ yrs) who underwent Tc-99m MAG3 diuretic scan due to suspicious unilateral obstructive uropathy were analyzed. DR with a $T_{1/2}\;of\;>\;15min$ was considered as positive for obstruction. DPT was considered to be present when there was delayed appearance of radioactivity in the renal pelvis and prolonged retention of radioactivity in the renal parenchyma. The renal area ratio was defined as the ratio of pixel number of hydronephrotic kidney over that of normal contralateral at $1{\sim}2min$ images. Definition of obstruction was improved hydronephrosis after intervention, or aggravated hydronephrosis without intervention. Non-obstruction was defined as unchanged hydronephrosis over 6 months. Results: Twenty-six renal units had obstruction and 28 no obstruction. The sensitivities of DR and DPT were 69% (18/26) and 50% (13/26) respectively. Two renal units with DPT but negative DR showed the renal area ratio of <1.1. Among the 20 obstructive renal units with DPT or positive DR, 13 with DPT had lower renal area ratio than 7 renal units without DPT ($0.97{\pm}0.20\;vs\;1.30{\pm}0.41,\;p<0.05$). Differential renal function was not significantly different between these groups. DPT correctly diagnosed all renal units with non-obstruction (specificity 100%), while the specificity of DR was 89% (25/28). Conclusion: DPT during Tc-99m MAG3 diuretic scan may be a valuable sign in diagnosing urinary obstruction especially in patients with false negative DR and early HN.