• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.422-425
• /
• 2008

TerraSAR-X is new radar satellite operated at X-band, multi polarization, and multi beam mode. Compared with C-band or L-band SAR, the X-band system inherently suffers from more temporal decorrelation, but is more sensitive to surface deformation monitoring due to short wavelength (3.1 cm) and high spatial resolution (1m-3m). It is generally expected that sensitivity to estimate surface movement using TerraSAR-X will be increased by the factor of 10, compared to current C-band system with low spatial resolution such as ERS-2, Envisat. Many urban areas are experiencing land subsidence due to water, oil and natural gas withdrawal, underground excavation, sediment compaction, and so on. Monitoring of surface deformation is valuable for effectively limiting damage areas. In addition high accuracy and spatially dense subsidence map can be achieved by X-band InSAR observation, promoting identification and separation of various subsidence processes and leading to enhanced understanding via mechanical modeling. In this study we will introduce some initial InSAR results using new TerraSAR-X SAR data for surface deformation monitoring.

• 천문학회보
• /
• 제43권1호
• /
• pp.70.1-70.1
• /
• 2018

The DEEP-South photometric census of small Solar System bodies is producing massive time-series data of variable, transient or moving objects as a by-product. To fully investigate unexplored variable phenomena, we present an application of multi-aperture photometry and FastBit indexing techniques to a portion of the DEEP-South year-one data. Our new pipeline is designed to do automated point source detection, robust high-precision photometry and calibration of non-crowded fields overlapped with area previously surveyed. We also adopt an efficient data indexing algorithm for faster access to the DEEP-South database. In this paper, we show some application examples of catalog-based variability searches to find new variable stars and to recover targeted asteroids. We discovered 21 new periodic variables including two eclipsing binary systems and one white dwarf/M dwarf pair candidate. We also successfully recovered astrometry and photometry of two near-earth asteroids, 2006 DZ169 and 1996 SK, along with the updated properties of their rotational signals (e.g., period and amplitude).

• 한국전자통신학회논문지
• /
• 제11권3호
• /
• pp.253-262
• /
• 2016

최근에 UWAC에 대한 연구가 많은 연구자와 학자들에 의해 연구되고 있다. DS-CDMA, OFDM, MIMO, 변조와 오류 보정 기법, 기타 기법들이 UWAC에서 고속으로 전송하기 위한 방법으로 사용할 수 있다. 본 논문에서는 배경이 없는 영역에서 도착시간을 추정하기 위한 이론을 검토하고 시간 차이를 계산한다, 또한 도착 시간 추정에 대한 기초적인 실험 결과를 제시한다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.679-681
• /
• 2003

The objectives of this research are as follows. First, to investigate methods for a national-scale land cover map based on multi-temporal classification of MODIS data and multi-spectral classification of Landsat TM data. Second, to investigate methods to p roduce ecological zone maps of Korea based on vegetation, climate, and topographic characteristics. The results of this research can be summarized as follows. First, NDVI and EVI of MODIS can be used to ecological mapping of the country by using monthly phenological characteris tics. Second, it was found that EVI is better than NDVI in terms of atmospheric correction and vegetation mapping of dense forests of the country. Third, several ecological zones of the country can be identified from the VI maps, but exact labeling requires much field works, and sufficient field data and macro-environmental data of the country. Finally, relationship between land cover types and natural environmental factors such as temperature, precipitation, elevation, and slope could be identified.

• 한국음향학회지
• /
• 제40권3호
• /
• pp.228-233
• /
• 2021

본 논문에서는 다양한 음악 템포 자극에 따라 변화하는 다채널 ElectroEncephaloGraphy(EEG)의 특징을 추출하고 분류하는 방식을 제안한다. 제안하는 방식에서 3차원 합성곱 양방향 게이트 순환 신경망은 전처리 과정 통해 변환된 3차원 EEG 입력 표현으로부터 시공간 및 긴 시간 종속적 특징을 추출한다. 실험 결과는 제안된 템포 자극 분류 방식이 기존의 방식보다 우수하며 음악 기반 뇌-컴퓨터 인터페이스를 구축할 수 있는 가능성을 보여준다.

• 한국멀티미디어학회논문지
• /
• 제23권12호
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.498-500
• /
• 2022

CCTV는 위험 상황을 파악하고 신속히 대응함으로써, 인명과 자산을 안전하게 보호한다. 하지만, 점점 많아지는 CCTV 영상을 지속적으로 모니터링하기는 어렵다. 이런 이유로 CCTV 영상을 지속적으로 모니터링하면서 이상행동이 발생했을 때 알려주는 장치가 필요하다. 최근 영상데이터 분석에 인공지능 모델을 활용한 많은 연구가 이루어지고 있다. 본 연구는 CCTV 영상에서 관측할 수 있는 다양한 이상 행동을 분류하기 위해 영상데이터 사이의 공간적, 시간적 특성 정보를 동시에 학습한다. 학습에 이용되는 인공지능 모델로 End-to-End 방식의 3D-Convolution Neural Network(CNN)와 ResNet을 결합한 다중 분류 딥러닝 모델을 제안한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권4호
• /
• pp.1066-1079
• /
• 2023

Multi-target tracking based on the detector is a very hot and important research topic in target tracking. It mainly includes two closely related processes, namely target detection and target tracking. Where target detection is responsible for detecting the exact position of the target, while target tracking monitors the temporal and spatial changes of the target. With the improvement of the detector, the tracking performance has reached a new level. The problem that always exists in the research of target tracking is the problem that occurs again after the target is occluded during tracking. Based on this question, this paper proposes a DeepSORT model based on SIFT features to improve ship tracking. Unlike previous feature extraction networks, SIFT algorithm does not require the characteristics of pre-training learning objectives and can be used in ship tracking quickly. At the same time, we improve and test the matching method of our model to find a balance between tracking accuracy and tracking speed. Experiments show that the model can get more ideal results.

• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• pp.6-10
• /
• 2023

High-potential data can be predicted and stored in the cache to prevent cache misses, thus reducing the processor's request and wait times. As a result, the processor can work non-stop, hiding memory latency. By utilizing the temporal/spatial locality of memory access, the prefetcher introduced to improve the performance of these computers predicts the following memory address will be accessed. We propose a prefetcher that applies the GRU model, which is advantageous for handling time series data. Display the currently accessed address in binary and use it as training data to train the Gated Recurrent Unit model based on the difference (delta) between consecutive memory accesses. Finally, using a GRU model with learned memory access patterns, the proposed data prefetcher predicts the memory address to be accessed next. We have compared the model with the multi-layer perceptron, but our prefetcher showed better results than the Multi-Layer Perceptron.

• Korean Journal of Radiology
• /
• 제23권9호
• /
• pp.854-865
• /
• 2022

Photon-counting detector (PCD) CT is a new CT technology utilizing a direct conversion X-ray detector, where incident X-ray photon energies are directly recorded as electronical signals. The design of the photon-counting detector itself facilitates improvements in spatial resolution (via smaller detector pixel design) and iodine signal (via count weighting) while still permitting multi-energy imaging. PCD-CT can eliminate electronic noise and reduce artifacts due to the use of energy thresholds. Improved dose efficiency is important for low dose CT and pediatric imaging. The ultra-high spatial resolution of PCD-CT design permits lower dose scanning for all body regions and is particularly helpful in identifying important imaging findings in thoracic and musculoskeletal CT. Improved iodine signal may be helpful for low contrast tasks in abdominal imaging. Virtual monoenergetic images and material classification will assist with numerous diagnostic tasks in abdominal, musculoskeletal, and cardiovascular imaging. Dual-source PCD-CT permits multi-energy CT images of the heart and coronary arteries at high temporal resolution. In this special review article, we review the clinical benefits of this technology across a wide variety of radiological subspecialties.