• 해양환경안전학회지
• /
• 제10권1호
• /
• pp.1-7
• /
• 2004

RADARSAT 위성은 레이더센서를 가지고 있어 전천후 및 주야불문이라는 두 가지 주요 이점을 가지고 있기 때문에, 선박탐지를 포함하는 해상감시 분야에 있어서 중요한 역할을 할 수 있다 그러나, 합성개구레이더의 이미징 시에 대기의 영향은 무시될 수 없으며, 또한 다양한 형태로 기하 변형이 발생하게 된다. 본 연구에서는, 레벨 1의 georeferenced SGX 데이터를 사용해서 RADARSAT의 합성개구레이더에 대한 대기/기하 보정을 실시하였다. 동일 이미지 내에서도, near range와 far range 세션의 비교를 위해서도 이와 같은 보정이 필요하다. 대기 보정은 후방산란에 대한 국소 조사부분과 입사각의 효과를 보정하여 수행되었으며, DN값은 beta nought와 sigma nought로 변환시켰다. 마지막으로 위성자세정보에서 추정되는 4점의 위치정보를 이용하여 자동 기하보정을 실시하였으며, 그 결과를 실제 좌표 값과 비교하였다. 오차는 위도방향으로 300m, 경도방향으로 260m범위 내에 있는 것으로 확인되었다. 이것은 추가로 지상기준점을 통해 보정될 수 있으며, 외해의 경우에는 적용 가능한 것으로 판단된다.

• 한국정보통신학회논문지
• /
• 제25권5호
• /
• pp.619-627
• /
• 2021

최근 드론은 가격 하락, 소형화와 함께 높은 기술 발전에 힘입어 드론 보급이 민군에 걸쳐 증가하면서 보안안전사고, 치안·안보 위협 등의 문제를 유발할 가능성도 커지고 있다. 드론으로 인해 발생하는 사건 및 사고를 예방하기 위해서는 드론의 출현에 대응할 수 있는 탐지 기술이 우선적으로 선행되어야 한다. 드론은 크기가 작고 전파 반사도가 낮은 재질로 구성되어 있어 음향, 적외선, 레이다의 운용만으로는 탐지가 어렵다. 최근 영상 식별 성능을 강화하기 위해 레이다 신호에 인공지능을 접목한 연구사례가 증가하는 추세이다. 본 논문에서는 레이다 영상을 이용한 드론 탐지 기술을 소개하며, 드론의 모의실험 데이터와 실제 실험 데이터를 기반으로 인공지능 기술에 적용하여 드론의 분류 정확도를 효과적으로 입증하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권10호
• /
• pp.5006-5022
• /
• 2017

Effect and robust detection of targets in infrared images has crucial meaning for many applications, such as infrared guidance, early warning, and video surveillance. However, it is not an easy task due to the special characteristics of the infrared images, in which the background clutters are severe and the targets are weak. The recent literature demonstrates that sparse representation can help handle the detection problem, however, the detection performance should be improved. To this end, in this text, a hybrid method based on local sparse representation and contrast is proposed, which can effectively and robustly detect the infrared targets. First, a residual image is calculated based on local sparse representation for the original image, in which the target can be effectively highlighted. Then, a local contrast based method is adopted to compute the target prediction image, in which the background clutters can be highly suppressed. Subsequently, the residual image and the target prediction image are combined together adaptively so as to accurately and robustly locate the targets. Based on a set of comprehensive experiments, our algorithm has demonstrated better performance than other existing alternatives.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권4호
• /
• pp.246-253
• /
• 2016

Infrared (IR) imaging has been researched for various applications such as surveillance. IR radiation has the capability to detect thermal characteristics of objects under low-light conditions. However, automatic segmentation for finding the object of interest would be challenging since the IR detector often provides the low spatial and contrast resolution image without color and texture information. Another hindrance is that the image can be degraded by noise and clutters. This paper proposes multi-level segmentation for extracting regions of interest (ROIs) and objects of interest (OOIs) in the IR scene. Each level of the multi-level segmentation is composed of a k-means clustering algorithm, an expectation-maximization (EM) algorithm, and a decision process. The k-means clustering initializes the parameters of the Gaussian mixture model (GMM), and the EM algorithm estimates those parameters iteratively. During the multi-level segmentation, the area extracted at one level becomes the input to the next level segmentation. Thus, the segmentation is consecutively performed narrowing the area to be processed. The foreground objects are individually extracted from the final ROI windows. In the experiments, the effectiveness of the proposed method is demonstrated using several IR images, in which human subjects are captured at a long distance. The average probability of error is shown to be lower than that obtained from other conventional methods such as Gonzalez, Otsu, k-means, and EM methods.

• International journal of advanced smart convergence
• /
• 제9권1호
• /
• pp.37-46
• /
• 2020

Cerebral vascular surgery can damage patients' motor and sensory nerves; therefore, neuromonitoring is performed intraoperatively. Patients with diabetes often have peripheral neuropathy and may be prone to nerve damage during surgery. This study aimed to identify factors that should be considered when diabetic patients undergo intraoperative neuromonitoring during brain vascular surgery and to present new criteria. Methods: In patients with and without diabetes who underwent cerebrovascular surgery (n = 30/group), we compared the intraoperative stimulation intensity, postoperative motor power and sensory, glycated hemoglobin (HbA1c) and glucose levels, and imaging findings. Results: Fasting glucose, blood glucose, and HbA1c levels were 10%, 12.1%, and 9.7%, respectively; they were higher in patients with than in patients without diabetes. Two patients with diabetes had weakness, and 10 required increased Somato sensory evoked potential (SSEP) stimulation, while in 16, motor power recovered over time rather than immediately. The non-diabetic group had no weakness after surgery, but 10 patients required more increased SSEP stimulation. The diabetic group showed significantly more abnormal test results than the non-diabetic group. Conclusion: For patients with diabetes undergoing surgery with intraoperative neuromonitoring, whether diabetic peripheral neuropathy is present, their blood glucose level and the anesthetic used should be considered.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권12호
• /
• pp.5286-5306
• /
• 2016

Emerging applications in automation, medical imaging, traffic monitoring and surveillance need real-time data transmission over Wireless Sensor Networks (WSNs). Guaranteeing Quality of Service (QoS) for real-time traffic over WSNs creates new challenges. Rapid penetration of smart devices, standardization of Machine Type Communications (MTC) in next generation 5G wireless networks have added new dimensions in these challenges. In order to satisfy such precise QoS constraints, in this paper, we propose a new cross-layer QoS-provisioning strategy in Wireless Multimedia Sensor Networks (WMSNs). The network layer performs statistical estimation of sensory QoS parameters. Identifying QoS-routing problem with multiple objectives as NP-complete, it discovers near-optimal QoS-routes by using evolutionary genetic algorithms. Subsequently, the Medium Access Control (MAC) layer classifies the packets, automatically adapts the contention window, based on QoS requirements and transmits the data by using routing information obtained by the network layer. Performance analysis is carried out to get an estimate of the overall system. Through the simulation results, it is manifested that the proposed strategy is able to achieve better throughput and significant lower delay, at the expense of negligible energy consumption, in comparison to existing WMSN QoS protocols.

• ETRI Journal
• /
• 제41권4호
• /
• pp.415-425
• /
• 2019

Generative adversarial networks (GAN) have been successfully used in many image restoration tasks, including image denoising, super-resolution, and compression artifact reduction. By fully exploiting its characteristics, state-of-the-art image restoration techniques can be used to generate images with photorealistic details. However, there are many applications that require faithful rather than visually appealing image reconstruction, such as medical imaging, surveillance, and video coding. We found that previous GAN-training methods that used a loss function in the form of a weighted sum of fidelity and adversarial loss fails to reduce fidelity loss. This results in non-negligible degradation of the objective image quality, including peak signal-to-noise ratio. Our approach is to alternate between fidelity and adversarial loss in a way that the minimization of adversarial loss does not deteriorate the fidelity. Experimental results on compression-artifact reduction and super-resolution tasks show that the proposed method can perform faithful and photorealistic image restoration.

• 한국군사과학기술학회지
• /
• 제25권4호
• /
• pp.329-338
• /
• 2022

This paper provides a case study of development testing and evaluation of design goal of Interferometric SAS (Synthetic Aperture Sonar) system that is developing supported by Civil-Military Technology Cooperation Center in offshore fields. For Deep water operating capabilities evaluation, We have surveyed candidate field, bathymetric mapping and target identification over 200 m depth, East Sea. In testing phase, We have provided environmental information of testing field include water column, seabed and weather condition in real time. And to compare excellency of developing InSAS, we have gather commercial imaging sonar system data with same target. This case study will support the Test Readiness Review of future underwater surveillance system developing via investigate marine testing field environment, testing facilities and planning.

• Journal of Positioning, Navigation, and Timing
• /
• 제10권4호
• /
• pp.235-242
• /
• 2021

Unmanned Aerial Vehicles (UAVs), which were used for military purposes, are gradually expanding their application fields under the influence of electrification and digitalization. Starting from the field of aerial imaging and Intelligence Surveillance and Reconnaissance (ISR) mission, nowadays the possibility of Urban Air Mobility (UAM), which transports passengers and cargo with drones, is widely under discussion. In order to occupy the rapidly growing global unmanned aerial vehicle market in advance, it is necessary to secure core technologies and develop key UAVs components based on the new technologies. In the navigation field, it is necessary to secure a precise position with guaranteed reliability and continuity, unrelated to the operating environments. The reliability and continuity should be secured in the algorithm level and in the H/W component levels also. In order to achieve this technical goal, the Ministry of Science and ICT has launched the 'Unmanned Vehicle Core Technology Research and Development Program' in 2019 to support the R&D on the unmanned vehicle technologies. In this paper, authors introduce the unmanned vehicle core technology research and development program to the related researchers. The authors summarize the backgrounds of the program and show the technological tasks and objectives on the sub-programs in the unmanned vehicle navigation program. We present the program schedules especially focused on the test and evaluation of the developed technologies and components.

• Clinical Endoscopy
• /
• 제57권4호
• /
• pp.434-445
• /
• 2024

Pancreatic cystic lesions (PCLs) have increased in prevalence due to the increased usage and advancements in cross-sectional abdominal imaging. Current diagnostic techniques cannot distinguish between PCLs requiring surgery, close surveillance, or expectant management. This has increased the morbidity and healthcare costs from inappropriately aggressive and conservative management strategies. Endoscopic ultrasound (EUS) needle-based confocal laser endomicroscopy (nCLE) allows for microscopic examination and delineation of the surface epithelium of PCLs. Landmark studies have identified characteristics distinguishing various types of PCLs, confirmed the high diagnostic yield of EUS-nCLE (especially for PCLs with an equivocal diagnosis), and shown that EUS-nCLE helps to change management and reduce healthcare costs. Refining procedure technique and reducing procedure length have improved the safety of EUS-nCLE. The utilization of artificial intelligence and its combination with other EUS-based advanced diagnostic techniques would further improve the results of EUS-based PCL diagnosis. A structured training program and device improvements to allow more complete mapping of the pancreas cyst epithelium will be crucial for the widespread adoption of this promising technology.