• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.229-239
• /
• 2019

All vegetation colonies have layered structure. This layer is called 'forest vertical structure.' Nowadays it is considered as an important indicator to estimate forest's vital condition, diversity and environmental effect of forest. So forest vertical structure should be surveyed. However, vertical structure is a kind of inner structure, so forest surveys are generally conducted through field surveys, a traditional forest inventory method which costs plenty of time and budget. Therefore, in this study, we propose a useful method to classify the vertical structure of forests using remote sensing aerial photographs and machine learning capable of mass data mining in order to reduce time and budget for forest vertical structure investigation. We classified it as SVM (Support Vector Machine) using RGB airborne photos and LiDAR (Light Detection and Ranging) DSM (Digital Surface Model) DTM (Digital Terrain Model). Accuracy based on pixel count is 66.22% when compared to field survey results. It is concluded that classification accuracy of layer classification is relatively high for single-layer and multi-layer classification, but it was concluded that it is difficult in multi-layer classification. The results of this study are expected to further develop the field of machine learning research on vegetation structure by collecting various vegetation data and image data in the future.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.1
• /
• pp.427-434
• /
• 2022

The purpose of this study is to create a self-portrait that provides an immersive experience that immerses the viewer into the problem of self-awareness. We propose a method to implement an interactive self-portrait by using audio and image information obtained from viewers. The viewer's voice information is converted into text and visualized. In this case, the viewer's face image is used as pixel information composing the text. Text is the result of a mixture of one's own emotions, imaginations, and intentions based on personal experiences and memories. People have different interpretations of certain texts in different ways.The proposed digital self-portrait not only reproduces the viewer's self-consciousness in the inner aspect by utilizing the intertextuality of the text, but also expands the meanings inherent in the text. Intertextuality in a broad sense refers to the totality of all knowledge that occurs between text and text, and between subject and subject. Therefore, the self-portrait expressed in text expands and derives various relationships between the viewer and the text, the viewer and the viewer, and the text and the text. In addition, this study shows that the proposed self-portrait can confirm the formativeness of text and re-create spatial and temporality in the external aspect. This dynamic self-portrait reflects the interests of viewers in real time, and has the characteristic of being updated and created.

• Journal of radiological science and technology
• /
• v.44 no.6
• /
• pp.623-627
• /
• 2021

Cervical foraminal stenosis is a disease in which the nerves that pass from the spinal canal to the limbs are narrowed and the nerves are compressed or damaged. Due to the lack of an imaging method that provides quantitatively stenosis, this study attempted to evaluate the area of the cervical vertebrae by reconstructing a three-dimensional computed tomography image, and to determine the area of the neural foramen in normal adults to calculate the stenosis rate. Using a three-dimensional image processing program, the surrounding bones including the posterior spinous process, lateral process, and lamellar bones of the cervical vertebra were removed so that the neural foramen could be observed well. A region of interest including the neural foraminal area of the three-dimensional image was set using ImageJ, and the number of pixels in the neural foraminal area was measured. The neural foraminal area was calculated by multiplying the number of measured pixels by the pixel size. To measure the largest neural foraminal area, it was measured between 40~50 degrees in the opposite direction and 15~20 degrees toward the head. The average area of the right C2-3 foramen was 44.32 mm², C3-4 area was 34.69 mm², C4-5 area was 36.41 mm², C5-6 area was 35.22 mm², C6-7 area was 36.03 mm². The average area of the left C2-3 foramen was 42.71 mm², C3-4 area was 32.23 mm², C5-6 area was 34.56 mm², and C6-7 area was 31.89 mm². By creating a reference table based on the neural foramen area of normal adults, the stenosis rate of patients with neural foraminal stenosis could be quantitatively calculated. It is expected that this method can be used as basic data for the diagnosis of cervical vertebral foraminal stenosis.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.541-548
• /
• 2021

Recently, multispectral cameras are being actively utilized in various application fields such as agriculture, forest management, coastal environment monitoring, and so on, particularly onboard UAV's. Resultant multispectral images are typically georeferenced primarily based on the onboard GPS (Global Positioning System) and IMU (Inertial Measurement Unit)or accurate positional information of the pixels, or could be integrated with ground control points that are directly measured on the ground. However, due to the high cost of establishing GCP's prior to the georeferencing or for inaccessible areas, it is often required to derive the positions without such reference information. This study aims to provide a means to improve the georeferencing performance of a multispectral camera images without involving such ground reference points, but instead with the simultaneously onboard high resolution RGB camera. The exterior orientation parameters of the drone camera are first estimated through the bundle adjustment, and compared with the reference values derived with the GCP's. The results showed that the incorporation of the images from a high resolution RGB camera greatly improved both the exterior orientation estimation and the georeferencing of the multispectral camera. Additionally, an evaluation performed on the direction estimation from a ground point to the sensor showed that inclusion of RGB images can reduce the angle errors more by one order.

• 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.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1925-1934
• /
• 2022

Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.5
• /
• pp.689-699
• /
• 2022

Recently, high productivity capabilities have been improved due to the application of advanced technologies in various industries, but in the construction industry, productivity improvements have been relatively low. Research on advanced technology for the construction industry is being conducted quickly to overcome the current low productivity. Among advanced technologies, 3D scan technology is widely used for creating 3D digital terrain models at construction sites. In particular, the 3D digital terrain model provides basic data for construction automation processes, such as earthwork machine guidance and control. The quality of the 3D digital terrain model has a lot of influence not only on the performance and acquisition environment of the 3D scanner, but also on the denoising, registration and merging process, which is a preprocessing process for creating a 3D digital terrain model after acquiring terrain scan data. Therefore, it is necessary to improve the terrain scan data processing performance. This study seeks to solve the problem of density inhomogeneity in terrain scan data that arises during the pre-processing step. The study suggests a 'pixel-based point cloud comparison algorithm' and verifies the performance of the algorithm using terrain scan data obtained at an actual earthwork site.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.1-12
• /
• 2022

Traditional methods of measuring corneal ulcers were difficult to present objective basis for diagnosis because of the subjective judgment of the medical staff through photographs taken with special equipment. In this paper, we propose a method to detect the ulcer area on a pixel basis in corneal ulcer images using a semantic segmentation model. In order to solve this problem, we performed the experiment to detect the ulcer area based on the DeepLab model which has the highest performance in semantic segmentation model. For the experiment, the training and test data were selected and the backbone network of DeepLab model which set as Xception and ResNet, respectively were evaluated and compared the performances. We used Dice similarity coefficient and IoU value as an indicator to evaluate the performances. Experimental results show that when 'crop & resized' images are added to the dataset, it segment the ulcer area with an average accuracy about 93% of Dice similarity coefficient on the DeepLab model with ResNet101 as the backbone network. This study shows that the semantic segmentation model used for object detection also has an ability to make significant results when classifying objects with irregular shapes such as corneal ulcers. Ultimately, we will perform the extension of datasets and experiment with adaptive learning methods through future studies so that they can be implemented in real medical diagnosis environment.

• 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 radiological science and technology
• /
• v.46 no.4
• /
• pp.315-323
• /
• 2023

Post-mortem computed tomography (PMCT) is commonly employed in the field of forensic pathology. PMCT was mainly performed using a whole-body scan with a wide field of view (FOV), which lead to a decrease in spatial resolution due to the increased pixel size. This study aims to evaluate the potential for developing a super-resolution model based on conditional generative adversarial networks (CGAN) to enhance the image quality of CT. 1761 low-resolution images were obtained using a whole-body scan with a wide FOV of the head phantom, and 341 high-resolution images were obtained using the appropriate FOV for the head phantom. Of the 150 paired images in the total dataset, which were divided into training set (96 paired images) and validation set (54 paired images). Data augmentation was perform to improve the effectiveness of training by implementing rotations and flips. To evaluate the performance of the proposed model, we used the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM) and Deep Image Structure and Texture Similarity (DISTS). Obtained the PSNR, SSIM, and DISTS values of the entire image and the Medial orbital wall, the zygomatic arch, and the temporal bone, where fractures often occur during head trauma. The proposed method demonstrated improvements in values of PSNR by 13.14%, SSIM by 13.10% and DISTS by 45.45% when compared to low-resolution images. The image quality of the three areas where fractures commonly occur during head trauma has also improved compared to low-resolution images.