http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
SAR 영상을 이용한 템플릿 매칭 기반 자동식별 알고리즘 구현 및 성능시험
임호,채대영,유지희,권경일,Lim, Ho,Chae, Daeyoung,Yoo, Ji Hee,Kwon, Kyung-Il 한국군사과학기술학회 2014 한국군사과학기술학회지 Vol.17 No.3
In this paper, we have developed a target recognition algorithm based on a template matching technique using Synthetic Aperture Radar (SAR) images. For efficient computations, Radon transform-based azimuth estimation algorithm was used with the template matching. MSTAR data set was divided into two groups according to the depression angles, which were a train set and a test set. Template data were generated by rotating and cropping chips which were from MSTAR train set using the azimuth estimation algorithm. Then the template matching process between test data and template data was performed under various conditions. Performance variation according to contrast enhancement preprocessing which is scarce in open literature was also presented. The analysis results show that the target recognition algorithm could be useful for the automatic target recognition using SAR images.
위성 SAR 영상의 지상차량 표적 데이터 셋 및 탐지와 객체분할로의 적용
박지훈,최여름,채대영,임호,유지희 한국군사과학기술학회 2022 한국군사과학기술학회지 Vol.25 No.1
The advent of deep learning-based algorithms has facilitated researches on target detection from synthetic aperture radar(SAR) imagery. While most of them concentrate on detection tasks for ships with open SAR ship datasets and for aircraft from SAR scenes of airports, there is relatively scarce researches on the detection of SAR ground vehicle targets where several adverse factors such as high false alarm rates, low signal-to-clutter ratios, and multiple targets in close proximity are predicted to degrade the performances. In this paper, a dataset of ground vehicle targets acquired from TerraSAR-X(TSX) satellite SAR images is presented. Then, both detection and instance segmentation are simultaneously carried out on this dataset based on the deep learning-based Mask R-CNN. Finally, this paper shows the future research directions to further improve the performances of detecting the SAR ground vehicle targets.
차원축소 없는 채널집중 네트워크를 이용한 SAR 변형표적 식별
박지훈,최여름,채대영,임호,Park, Ji-Hoon,Choi, Yeo-Reum,Chae, Dae-Young,Lim, Ho 한국군사과학기술학회 2022 한국군사과학기술학회지 Vol.25 No.3
In implementing a robust automatic target recognition(ATR) system with synthetic aperture radar(SAR) imagery, one of the most important issues is accurate classification of target variants, which are the same targets with different serial numbers, configurations and versions, etc. In this paper, a deep learning network with channel attention modules is proposed to cope with the recognition problem for target variants based on the previous research findings that the channel attention mechanism selectively emphasizes the useful features for target recognition. Different from other existing attention methods, this paper employs the channel attention modules without dimensionality reduction along the channel direction from which direct correspondence between feature map channels can be preserved and the features valuable for recognizing SAR target variants can be effectively derived. Experiments with the public benchmark dataset demonstrate that the proposed scheme is superior to the network with other existing channel attention modules.
고속 Chirplet 분리기법을 이용한 VHF 대역 레이더 표적신호 모델링 및 해석
박지훈,김시호,채대영 한국군사과학기술학회 2019 한국군사과학기술학회지 Vol.22 No.4
Although radar target signatures(RTS), such as range profiles have played an important role for target recognition in the X-band radar, they would be less effective when a target is designed to have low radar cross section(RCS). Recently, a number of research groups have conducted the studies on the RTS in the VHF-band where such targets can be better detected than in the X-band. However, there is a lack of work carried out on the mathematical description of the VHF-band RTS. In this paper, chirplet decomposition is employed for modeling of the VHF-band RTS and its performance is compared with that of existing scattering center model generally used for the X-band. In addition, the discriminative signal analysis is performed by chirplet parameterization of range profiles from in an ISAR image. Because the chirplet decomposition takes long computation time, its fast form is further proposed for enhanced practicality.
서승모,최여름,임 호,채대영 한국전자파학회 2022 Journal of Electromagnetic Engineering and Science Vol.22 No.3
The proposed approach achieves the reliable accuracy of synthetic aperture radar-automatic target recognition (SAR-ATR) with a simulation database. The simulation images of targets-of-interest are generated from inverse SAR using high-frequency techniques. A measurement image translation-automatic target recognition (MIT-ATR) uses two deep learning networks. The unique feature of the MIT-ATR is that the measurement images are translated to the simulation-like images by cycle generative adversarial network (CycleGAN). CycleGAN does not need to have a dataset of paired images between the measurement and simulation images. The generated simulation-like images are used as the inputs of the Visual Geometry Group (VGG) network. The VGG network is trained on a simulation database with a softmax layer of multi-classes. Five classes, including a T-72 tank, are considered in the numerical experiments. The images of each class are simulated at all azimuth angles, but the elevation angles range from 6° to 30°. The accuracy of the proposed approach is 63% better than that of the traditional method with only the VGG network. The simulation database could definitely supplement the lack of measurement data. The accuracy of MIT-ATR is properly handled by CycleGAN and the VGG network.
이현수(Hyunsoo Lee),정기환(Ki-Hwan Jung),채대영(Dae-Young Chae),고일석(Il-Suek Koh) 한국전자파학회 2014 한국전자파학회논문지 Vol.25 No.5
IPO(Iterative Physical Optics) 방법은 대규모 물체의 산란파를 효과적으로 계산하는 고주파 근사 방법 중 하나인 PO(Physical Optics) 방법을 반복적으로 적용하는 계산방법이다. IPO 방법은 일차(first-order) PO 방법에서는 고려하지 못하는 다중 반사를 고려할 수 있어, 산란체 표면에 여기되는 전류의 정확도를 높일 수 있다. 그러므로 산란체의 RCS(Radar Cross Section)를 보다 정확하게 예측할 수 있다. 그러나 IPO 방법은 필요한 적분방정식을 정확하게 풀지 않아 수렴성에 문제가 생긴다. 그러므로 본 논문에서는 IPO 방법의 수렴성을 조절하기 위해, 행렬연산에 사용하는 Jacobi, Gauss-Seidel, SOR(Successive Over Relaxation) 그리고 Richardson 방법을 IPO 방법에 적용하였다. 그러므로 대규모 물체의 RCS 계산을 제안된 IPO 방법을 사용하여 효율적으로 계산할 수 있다. 또, 이들의 정확도를 시뮬레이션을 통해 검증하였다. The IPO(Iterative Physical Optics) method repeatedly applies the well-known PO(Physical Optics) approximation to calculate the scattered field by a large object. Thus, the IPO method can consider the multiple scattering in the object, which is ignored for the PO approximation. This kind of iteration can improve the final accuracy of the induced current on the scatterer, which can result in the enhancement of the accuracy of the RCS(Radar Cross Section) of the scatterer. Since the IPO method can not exactly but approximately solve the required integral equation, however, the convergence of the IPO solution can not be guaranteed. Hence, we apply the famous techniques used in the inversion of a matrix to the IPO method, which include Jacobi, Gauss-Seidel, SOR(Successive Over Relaxation) and Richardson methods. The proposed IPO methods can efficiently calculate the RCS of a large scatterer, and are numerically verified.
이창섭,Ju-Hyung Lee,Mi-Ra Oh,최경민,정미란,Jong-Dae Park,권대영,Ki-Chan Ha,Eun-Ock Park,Nuri Lee,Sun-Young Kim,Eun-Kyung Choi,김민걸,채수완 대한의학회 2012 Journal of Korean medical science Vol.27 No.12
Korean Red Ginseng (KRG) is a functional food and has been well known for keeping good health due to its anti-fatigue and immunomodulating activities. However, there is no data on Korean red ginseng for its preventive activity against acute respiratory illness (ARI). The study was conducted in a randomized, double-blinded, placebo-controlled trial in healthy volunteers (Clinical Trial Number: NCT01478009). Our primary efficacy end point was the number of ARI reported and secondary efficacy end point was severity of symptoms,number of symptoms, and duration of ARI. A total of 100 volunteers were enrolled in the study. Fewer subjects in the KRG group reported contracting at least 1 ARI than in the placebo group (12 [24.5%] vs 22 [44.9%], P = 0.034), the difference was statistically significant between the two groups. The symptom duration of the subjects who experienced the ARI, was similar between the two groups (KRG vs placebo; 5.2 ± 2.3 vs 6.3 ± 5.0, P = 0.475). The symptom scores were low tendency in KRG group (KRG vs placebo; 9.5 ± 4.5 vs 17.6 ± 23.1, P = 0.241). The study suggests that KRG may be effective in protecting subjects from contracting ARI, and may have the tendency to decrease the duration and scores of ARI symptoms.