• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.143-156
• /
• 2023

To precisely and reliably analyze the contents of the satellite imagery, recognizing the clouds which are the obstacle to gathering the useful information is essential. In recent times, deep learning yielded satisfactory results in various tasks, so many studies using deep neural networks have been conducted to improve the performance of cloud detection. However, existing methods for cloud detection have the limitation on increasing the performance due to the adopting the network models for semantic image segmentation without modification. To tackle this problem, we introduced the multi-branch neural architecture search to find optimal network structure for cloud detection. Additionally, the proposed method adopts the soft intersection over union (IoU) as loss function to mitigate the disagreement between the loss function and the evaluation metric and uses the various data augmentation methods. The experiments are conducted using the cloud detection dataset acquired by Arirang-3/3A satellite imagery. The experimental results showed that the proposed network which are searched network architecture using cloud dataset is 4% higher than the existing network model which are searched network structure using urban street scenes with regard to the IoU. Also, the experimental results showed that the soft IoU exhibits the best performance on cloud detection among the various loss functions. When comparing the proposed method with the state-of-the-art (SOTA) models in the field of semantic segmentation, the proposed method showed better performance than the SOTA models with regard to the mean IoU and overall accuracy.

• Korean Journal of Remote Sensing
• /
• v.34 no.2_1
• /
• pp.295-300
• /
• 2018

Net radiation is the total amount of radiation energy used as a heat flux for the Earth's energy cycle, and net radiation from the surface is an important factor in areas such as hydrology, climate, meteorological studies and agriculture. It is very important to monitoring the net radiation through remote sensing to be able to understand the trend of heat island and urbanization phenomenon. However, net radiation estimation using only remote sensing data is generally causes difference in accuracy depending on cloud. Therefore, in this paper, we retrieved and monitored high resolution surface net radiation at 1 hour interval in Eunpyeong New Town where urbanization using Communication, Ocean and Meteorological Satellite (COMS), Landsat-8 satellite and Computational Fluid Dynamics (CFD) model data reflecting the difference in building height. We compared the observed and estimated net radiation at the flux tower. As a result, estimated net radiation was similar trend to the observed net radiation as a whole and it had the accuracy of RMSE $54.29Wm^{-2}$ and Bias $27.42Wm^{-2}$. In addition, the calculated net radiation showed well the meteorological conditions such as precipitation, and showed the characteristics of net radiation for the vegetation and artificial area in the spatial distribution.

• ETRI Journal
• /
• v.40 no.2
• /
• pp.167-179
• /
• 2018

This paper proposes an IEEE 802.15.4m compliant TV white-space orthogonal frequency-division multiplexing (TVWS)-(OFDM) radio frequency (RF) transceiver that can be adopted in advanced metering infrastructures, universal remote controllers, smart factories, consumer electronics, and other areas. The proposed TVWS-OFDM RF transceiver consists of a receiver, a transmitter, a 25% duty-cycle local oscillator generator, and a delta-sigma fractional-N phase-locked loop. In the TV band from 470 MHz to 698 MHz, the highly linear RF transmitter protects the occupied TV signals, and the high-Q filtering RF receiver is tolerable to in-band interferers as strong as -20 dBm at a 3-MHz offset. The proposed TVWS-OFDM RF transceiver is fabricated using a $0.13-{\mu}m$ CMOS process, and consumes 47 mA in the Tx mode and 35 mA in the Rx mode. The fabricated chip shows a Tx average power of 0 dBm with an error-vector-magnitude of < 3%, and a sensitivity level of -103 dBm with a packet-error-rate of < 3%. Using the implemented TVWS-OFDM modules, a public demonstration of electricity metering was successfully carried out.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.2
• /
• pp.60-67
• /
• 2007

This paper describes the development of on-line computer vision laboratories to teach the detailed image processing and pattern recognition techniques. The computer vision laboratories include distant image acquisition method, basic image processing and pattern recognition methods lens and light, and communication. This study introduces a case study that teaches computer vision in distance learning. environment. It shows a schematic of a distant teaming workstation and contents of laboratories with image processing examples. The study focus more on the contents of the vision Labs rather than internet application method. The study proposes the ways to improve the on-line computer vision laboratories and includes the further research perspectives.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.448-454
• /
• 2003

This paper concerns the establishment of the Internet-based virtual laboratory (VL). In control engineering, it is required to evaluate the feasibility of a newly developed controller design technique by applying to a physical system. However, it is inefficient to make or build such a experimental apparatus in all research activities. A possible remedy is to share such a apparatus spatially via the Internet. We set up techniques for the remote -control of various experimental apparatuses based on the Internet. The proposed VL forms a server-client structure and is implemented in multi-control interfaces.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1520-1542
• /
• 2020

Traditional software testing typically uses many physical resources to manually build various test environments, resulting in high resource costs and long test time due to limited resources, especially for small enterprises. Cloud computing can provide sufficient low-cost virtual resources to alleviate these problems through the virtualization of physical resources. However, the provision of various test environments and services for implementing software testing rapidly and conveniently based on cloud computing is challenging. This paper proposes a multilayer cloud testing model based on cloud computing and implements a hybrid cloud testing system based on virtual machines (VMs) and networks. This system realizes the automatic and rapid creation of test environments and the remote use of test tools and test services. We conduct experiments on this system and evaluate its applicability in terms of the VM provision time, VM performance and virtual network performance. The experimental results demonstrate that the performance of the VMs and virtual networks is satisfactory and that this system can improve the test efficiency and reduce test costs through rapid virtual resource provision and convenient test services.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.429-434
• /
• 2002

The Synthetic Aperture Radar (SAR) data are considered to contain the greatest amount of information among various microwave techniques developed for measuring ocean variables from aircraft or satellites. They have the potential of measuring wavelength, wave direction and wave height of the ocean waves. But, it is difficult to retrieve significant ocean wave heights and surface current from conventional SAR data, since the imaging mechanism of ocean waves by a SAR is determined by the three basic modulation processes arise through the tilt modulation, hydrodynamic modulation and velocity bunching which are poorly known functions. Along-Track Interferometric (ATI) SAR systems can directly detect the Doppler shift associated with each pixel of a SAR image and have been used to estimate wave fields and surface currents. However, the Doppler shift is not simply proportional to the component of the mean surface current. It includes also contributions associated with the phase velocity of the Brags waves and orbital motions of all ocean waves that are longer than Brags waves. In this paper, we have developed a new method for extracting the surface current vector using multiple-frequency (L- & C-band) ATI SAR data, and have generated surface wave height information.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.460-464
• /
• 2002

Multitemporal interferometric SAR has became an useful geodetic tool for monitoring Earth's surface deformation, generation of precise DEM, and land cover classification even though there still exist certain constraints such as temporal and spatial decorrelation effects, atmospheric artifacts and inaccurate orbit information. The Korea where nearly all areas are heavily vegetated, JERS-1 SAR has advantages in monitoring surface deformations and environmental changes in that it uses 4-times longer wavelength than ERS-l/2 or RADARSAT SAR system. For generating differential SAR interferogram and differential coherence image fer deformation mapping and temporal change detection, respectively, topographic phase removal process is required utilizing a reference inteferogram or external DEM simulation. Because the SAR antenna baseline parameter for JERS-1 is less accurate than those of ERS-l/2, one can not estimate topographic phases from an external DEM and the residual phase appears in differential interferogram. In this paper, we examined topographic phase retrieval method utilizing an external DEM. The baseline refinement is carried out by minimizing the differences between the measured unwrapped phase and the reference points of the DEM.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.134-137
• /
• 2005

Unsupervised spectral angle classification (USAC) is the algorithm that can extract ground object information with the minimum 'Spectral Angle' operation on behalf of 'Spectral Euclidian Distance' in the clustering process. In this study, our algorithm uses the unit vector instead of the spectral distance to compute the mean of cluster in the unsupervised classification. The proposed algorithm (MUSAC) is applied to the Hyperion and ETM+ data and the results are compared with K-Meails and former USAC algorithm (FUSAC). USAC is capable of clearly classifying water and dark forest area and produces more accurate results than K-Means. Atmospheric correction for more accurate results was adapted on the Hyperion data (Hyperion-FLAASH) but the results did not have any effect on the accuracy. Thus we anticipate that the 'Spectral Angle' can be one of the most accurate classifiers of not only multispectral images but also hyperspectral images. Furthermore the cluster unit vector can be an efficient technique for determination of each cluster mean in the USAC.

• Biomedical Science Letters
• /
• v.10 no.4
• /
• pp.495-499
• /
• 2004

Because the education system that based on objective data is needed for the beginning technologists in the department of medicine laboratory, development of the CAI system based on Gram-Stain images is needed in clinical microbiology field. So, in this study, we implemented CAI system based on Gram-Stain images for medical technologists under Web using multimedia toolbook. Because this system is implemented under Web, more and more beginning technologists can have a remote-education beyond time and space, can save human power and time that needed due to hold in common of educational information, and cannot learn mistaken microbiology images because of learning execution based on objective data. Also, implemented system brings a higher interest and a learning effect to medical technologies because of hyper-media method that offered from toolbook. In the future, it will be needed a continuous acceptance of changing knowledge and it will be useful system for technologist in case of applying various examinations based Gram-Stain method of this study.