• 대한원격탐사학회지
• /
• 제38권1호
• /
• pp.111-126
• /
• 2022

Land use and land cover (LULC) mapping is an important factor in geospatial analysis. Although highly precise ground-based LULC monitoring is possible, it is time consuming and costly. Conversely, because the synthetic aperture radar (SAR) sensor is an all-weather sensor with high resolution, it could replace field-based LULC monitoring systems with low cost and less time requirement. Thus, LULC is one of the major areas in SAR applications. We developed a LULC model using only KOMPSAT-5 single co-polarized data and digital elevation model (DEM) data. Twelve HH-polarized images and 18 VV-polarized images were collected, and two HH-polarized images and four VV-polarized images were selected for the model testing. To train the LULC model, we applied the conditional generative adversarial network (cGAN) method. We used U-Net combined with the residual unit (ResUNet) model to generate the cGAN method. When analyzing the training history at 1732 epochs, the ResUNet model showed a maximum overall accuracy (OA) of 93.89 and a Kappa coefficient of 0.91. The model exhibited high performance in the test datasets with an OA greater than 90. The model accurately distinguished water body areas and showed lower accuracy in wetlands than in the other LULC types. The effect of the DEM on the accuracy of LULC was analyzed. When assessing the accuracy with respect to the incidence angle, owing to the radar shadow caused by the side-looking system of the SAR sensor, the OA tended to decrease as the incidence angle increased. This study is the first to use only KOMPSAT-5 single co-polarized data and deep learning methods to demonstrate the possibility of high-performance LULC monitoring. This study contributes to Earth surface monitoring and the development of deep learning approaches using the KOMPSAT-5 data.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.101-103
• /
• 2022

중요시설 실시간 감지 시스템으로는 주로 CCTV를 사용하고 있다. CCTV의 경우 감지에 대한 정확성은 높지만 시야각이 좁기 때문에 레이다(RADAR)와 같은 센서와 함께 혼용되어 사용되고 있다. 라이다(LiDAR)는 고출력의 펄스 레이저를 이용하여 물체에 반사되어 돌아오는 시간을 감지하여 거리정보를 획득하는 기술이다. 라이다의 경우 데이터 처리량으로 인해 서버의 동시 처리 센서 개수의 제약으로 인해 비용적으로나 기술적으로나 활용도가 높지 않은 문제점이 있다. 광망 센서에 의한 감지 방식 또한 강풍과 혹한에 취약하고 동물 훼손에 따른 유지보수의 문제도 있다. 본 논문에서는 기존의 라이다 센서에서 사용하는 905nm 파장대가 아닌 1550nm 파장대를 사용함으로써 기상 환경에 대한 영향은 강하고, 다수의 센서를 통합하여 관제할 수 있는 시스템 개발을 제안하고자 한다.

• 신재생에너지
• /
• 제9권3호
• /
• pp.14-19
• /
• 2013

Comparative evaluation of offshore wind retreival software, which use the satellite images taken by Synthetic Aperture Radar sensor; SARTools of CLS-SOPRONO, France and SpaceEye of London Research and Development Corporation, Canada is carried out. For a reference satellite image, ENVISAT ASAR imagery of Jeollanam-do Wan-do area when the winter-time northwestern wind prevails is processed by CMOD_IFR2, CMOD4, CMOD5 algorithms. Wind speed difference and its relative ratio are calculated to evaluate uncertainty of software selection.

• Journal of Mechanical Science and Technology
• /
• 제19권9호
• /
• pp.1742-1752
• /
• 2005

This paper presents a Multiple Target Tracking (MTT) Adaptive Cruise Control (ACC) system which consists of three parts; a multi-model-based multi-target state estimator, a primary vehicular target determination algorithm, and a single-target adaptive cruise control algorithm. Three motion models, which are validated using simulated and experimental data, are adopted to distinguish large lateral motions from longitudinally excited motions. The improvement in the state estimation performance when using three models is verified in target tracking simulations. However, the performance and safety benefits of a multi-model-based MTT-ACC system is investigated via simulations using real driving radar sensor data. The MTT-ACC system is tested under lane changing situations to examine how much the system performance is improved when multiple models are incorporated. Simulation results show system response that is more realistic and reflective of actual human driving behavior.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.389-389
• /
• 2000

The number of automobiles is rapidly increasing , as are the importance of the car as a way of transportation, and the variety of its uses. In these surroundings, a safety, one of the primary factors which must be considered in automotive engineering, demands a system that aids the driver's vision and perception. In this point of view, development of the more promoted system that complement the existing passive method which relies on just man's ability is the important issue of the advanced traffic system including ITS. In this paper, we provide an algorithm and implementation of a control system that warns the collisions ahead and avoids this situation, using informations about the host-car, target-car and surroundings. The warning is made by an algorithm that decides the degree of safely. With this degree of safely, the controller automatically controls a vehicle's speed to a proper level.

• 한국군사과학기술학회지
• /
• 제8권1호
• /
• pp.25-31
• /
• 2005

PLA(Passive Linear Array) system has been primarily utilized to detect and track underwater targets, such as submarines. This system has difficulty in distinguishing between underwater targets and surface ships in a dense target environment. And a single-PLA system does not provide target state observability. At least two PLAs are necessary to observe a track uniquely. To classify and localize the underwater targets effectively, first of all, it is very of importance to discriminate the surface ships in the multi-target environment. These problems can be overcome by the association of distributed PLAs and radars. In this paper, we present an algorithm to solve the track-to-track association of the heterogeneous data from three PLAs and one radar are noncollocated with known sensor positions. Also, this paper shows the simulation results to verify the proposed algorithm.

• 한국군사과학기술학회지
• /
• 제14권3호
• /
• pp.474-481
• /
• 2011

The Electronic Warfare Computer for the Aircraft Survivability Equipment will improve the ability for countermeasures by analysis about threat information. This paper suggests method that threat data integration of multiple sensors(Radar Warning Receiver, Laser Warning Receiver, Missile Warning Receiver). The algorithm of threat data integration is based on detected threat sequence and azimuth information. The threat sequence information is analyzed in advance and the azimuth data is received from sensors. The suggested method is evaluated through simulation under the environment like real helicopter.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 추계학술대회
• /
• pp.82-85
• /
• 2018

카메라를 이용하여 특정 범위에 객체 침입을 탐지하는 시스템이 많아지고 있다. 하지만 이러한 카메라를 이용한 객체 침입 탐지는 실내에 설치되어 사용되는 경우가 많고, 외부에서 사용할 경우 환경적인 요인(비, 바람 등에 날리는 물체들)에 의해 정확도가 떨어지는 경우가 많다. 또한, 센서만 사용하여 침입을 탐지하는 시스템은 센서의 감지 범위에 따라 설치할 수 있는 공간이 제약되고 일정 크기 이상의 공간에서 사용할 수 없다는 단점이 있다. 본 논문에서 제안하는 침입 탐지 시스템은 레이저, 초음파, 인체감지 센서의 단점인 감지 범위를 보완할 수 있는 레이더 센서와 카메라를 이용하여 감시 영역 내의 침입을 탐지하는 시스템을 설계하였다.

• 전기학회논문지
• /
• 제59권11호
• /
• pp.1980-1985
• /
• 2010

This paper is about design of optimal structure of slot antenna array antenna with inner waveguide in accordance with the slot model, and fabrication of its prototype sample operating at the frequency of 24 GHz. Results of this work can be employed as a useful tool to develop and diversify slot antenna having superior performance and omni-directivity to that of current antenna. The implemented antenna demonstrates ultra-wideband performance for frequency ranges 24 GHz with the relatively high and flat antenna gain of 18.64dBi and low sidelobe levels. In addition, a $2{\times}8$ antenna array for phased-array systems and mm-wave sensor applications is also presented.

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1505-1515
• /
• 2016

The age of autonomous vehicles has come according to development of high performance sensing and artificial intelligence technologies. And importance of the vehicle's surrounding environment sensing and observation is increasing accordingly because of its stability and control efficiency. In this paper we propose an integrated platform for efficient networking, analysis and monitoring of multiple sensing data on the vehicle that are equiped with various automotive sensors such as GPS, weather radar, automotive radar, temperature and humidity sensors. From simulation results, we could see that the proposed platform could perform realtime analysis and monitoring of various sensing data that were observed from the vehicle sensors. And we expect that our system can support drivers or autonomous vehicles to recognize optimally various sudden or danger driving environments on the road.