• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.1
• /
• pp.63-73
• /
• 2021

This paper presents a algorithm for automatic target recognition robust to the influence of the flame in order to track the target by EOTS(Electro-Optical Targeting System) equipped on UAV(Unmanned Aerial Vehicle) when there is aerial target or marine target with flame at the same time. The proposed method converts infrared images of targets and flames into a gradient vector field, and applies each gradient magnitude to a polynomial curve fitting technique to extract polynomial coefficients, and learns them in a shallow neural network model to automatically recognize targets and flames. The performance of the proposed technique was confirmed by utilizing the various infrared image database of the target and flame. Using this algorithm, it can be applied to areas where collision avoidance, forest fire detection, automatic detection and recognition of targets in the air and sea during automatic flight of unmanned aircraft.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.381-384
• /
• 2012

본 연구에서는 가상전시 시스템에서 제품의 시각적 디자인에 대한 고객의 관심도를 자동으로 평가하기 위한 영상분석 기법을 제시한다. 전시공간의 동영상으로부터 모션인식, 목표물 감지 및 추적기법을 통하여 기본 특징을 추출하고 이로부터 대상자의 행동패턴을 인식한다. 정의된 각 행동패턴에 따라 상품의 관심도와의 관계를 반영하는 가중치 파라미터를 정의하였으며 이에 대한 학습알고리즘을 제안하였다. 실험으로서 4종류, 종 24개 제품에 대하여 제안된 방법을 적용한 결과를, 직접조사를 통한 실제 관심도 자료와 비교하여 분석함으로써 제안된 기법의 유용성을 평가하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10a
• /
• pp.94-96
• /
• 2004

에이전트의 '물체 따라가기'는 전통적으로 자동운전이나 가이드 등의 다양한 서비스를 제공할 수 있는 기본적인 기능이다. 여러 가지 물체가 있는 환경에서 '물체 따라가기'를 하기 위해서는 목적하는 대상이 어디에 있는지 찾을 수 있어야 하며, 실제 환경에는 사람이나 차와 같이 움직이는 물체들이 존재하기 때문에 다른 물체들을 피할 수 있어야 한다. 그런데 에이전트의 최적화된 피하기 행동은 장애물의 모양과 크기에 따라 다르게 생성될 수 있다. 본 논문에서는 다양한 모양과 크기의 장애물이 있는 환경에서 최적의 피하기 행동을 생성하면서 물체를 추적하기 위해 반응형 에이전트의 행동선택을 강화학습 한다. 여기에서 정확하게 상태를 인식하기 위하여 상태를 추론하고 목표물과 일정거리를 유지하기 위해 베이지안 추론을 이용한다 베이지안 추론은 센서정보를 이용해 확률 테이블을 생성하고 가장 유력한 상황을 추론하는데 적합한 방법이고, 강화학습은 실시간으로 장애물 종류에 따른 상태에서 최적화된 행동을 생성하도록 평가함수를 제공하기 때문에 베이지안 추론과 강화학습의 결합모델로 장애물에 따른 최적의 피하기 행동을 생성할 수 있다. Webot을 이용한 시뮬레이션을 통하여 다양한 물체가 존재하는 환경에서 목적하는 대상을 따라가면서 이종의 움직이는 장애물을 최적화된 방법으로 피할 수 있음을 확인하였다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.38 no.11
• /
• pp.1123-1129
• /
• 2010

Angular Deviation(AD) on transparency applied to TA-50 Aircraft deteriorates armament system's accuracy because it makes a difference in between actual and theoretical targets. In order to increase accuracy, therefore, TA-50 Aircraft measures AD on transparency and provide the measured values for the integrated mission display computer as a type of AD coefficients. This makes AD revised so that pilots can accurately see the actual target on their head-up display. In order to implement such mechanism into a real field, we develop a new device and system automatically measuring AD for the first time. We also deal with basic concept including AD induction formula as well as operating systems. As a consequence of testing the accuracy and precision for verifying reliability of the system, we got satisfactory results. In specific, the accuracy was within the resultant criterion of 1%. The precision was also satisfied with respect to the whole criteria. The system developed through this research is qualified as a military standard equipment for transparency of the canopy.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.3
• /
• pp.203-216
• /
• 2003

In this paper a new feature extraction and target classification method is proposed for the recognition part of FLIR(Forwar Looking Infrared)-image-based ATR system. Proposed feature extraction method is "cluster(=set of classes)-based"version of previous fisherfaces method that is known by its robustness to illumination changes in face recognition. Expecially introduced class clustering and cluster-based projection method maximizes the performance of fisherfaces method. Proposed target image classification method is based on the mixture of experts model which consists of RBF-type experts and MLP-type gating networks. Mixture of experts model is well-suited with ATR system because it should recognizee various targets in complexed feature space by variously mixed conditions. In proposed classification method, one expert takes charge of one cluster and the separated structure with experts reduces the complexity of feature space and achieves more accurate local discrimination between classes. Proposed feature extraction and classification method showed distinguished performances in recognition test with customized. FLIR-vehicle-image database. Expecially robustness to pixelwise sensor noise and un-wanted intensity variations was verified by simulation.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.44 no.5
• /
• pp.407-415
• /
• 2016

In this paper, an aviation image fusion method is proposed for creating an informative fused image through gray scale images within noise. The proposed method is based on an adaptive guided filter which adjusts regulation parameter of the filter based on peak signal noise ratio (PSNR) in order to behave as an edge-preserving filtering property. Simulation results demonstrate that the proposed method preserves the edge information of the input image and reduces the noise effect while maintaining designed PSNR.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.24 no.6
• /
• pp.77-84
• /
• 2020

In this paper, we developed a damage evaluation technique that can determine the damage location of a long-sized structure such as a cable-stayed bridge, and verified the performance of the developed technique through experiments. The damage assessment method aims to extract data that can evaluate the damage of the structure without the undamage data and can determine the damage location only by analyzing the response data of the structure. To complete this goal, we developed a damage assessment technique that considers variability based on the IMD theory, which is a statistical pattern recognition technique, to identify the damage location. To complete this goal, we developed a damage assessment technique that considers variability based on the IMD theory, which is a statistical pattern recognition technique, to identify the damage location. To evaluate the performance of the developed technique experimentally, cable damage experiments were conducted on model cable-stayed bridges. As a result, the damage assessment method considering variability automatically outputs the damageless data according to external force, and it is confirmed that the performance of extracting information that can determine the damage location of the cable through the analysis of the outputted damageless data and the measured damage data is shown.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.24 no.1
• /
• pp.111-121
• /
• 2006

Recently, many studies have been performed to apply airborne LIDAR data to extracting urban models. In order to model efficiently the man-made objects which are the main components of these urban models, it is important to extract automatically planar patches from the set of the measured three-dimensional points. Although some research has been carried out for their automatic extraction, no method published yet is sufficiently satisfied in terms of the accuracy and completeness of the segmentation results and their computational efficiency. This study thus aimed to developing an efficient approach to automatic segmentation of planar patches from the three-dimensional points acquired by an airborne LIDAR system. The proposed method consists of establishing adjacency between three-dimensional points, grouping small number of points into seed patches, and growing the seed patches into surface patches. The core features of this method are to improve the segmentation results by employing the variable threshold value repeatedly updated through a statistical analysis during the patch growing process, and to achieve high computational efficiency using priority heaps and sequential least squares adjustment. The proposed method was applied to real LIDAR data to evaluate the performance. Using the proposed method, LIDAR data composed of huge number of three dimensional points can be converted into a set of surface patches which are more explicit and robust descriptions. This intermediate converting process can be effectively used to solve object recognition problems such as building extraction.

• Economic and Environmental Geology
• /
• v.38 no.6 s.175
• /
• pp.643-656
• /
• 2005

The East Sea, a marginal sea or back-arc basin, consists of Japan Basin, Yamato Basin, and Ulleung Basin and is surrounded by the Pacific Plate and Philippine Sea Plate. Ulleung Basin locates in the southwestern part of the East Sea and shows the depth of 1,500 m in average and 2,500 m in maximum, connecting to the Japan Basin along 2,000 m contour. The slope of the seafloor is greater in the western side of the basin than in the southern and the eastern side. The crustal thickness of the Ulleung Basin from the OBS tends to get thicker toward the north and the west side and the sediment thickness of the Ulleung Basin is getting thicker toward the southeast side and reaches up to 12 km. The crustal type of the Ulleung Basin was variously suggested as like as a rifted continental crust, an extended continental crust, and an incipient oceanic trust. The origin of the crustal formation and the Ulleung Basin, however, is still controversial. Based on the bathymetry and gravtiy anomaly data for this study, the axis of the Ulleung Basin shows that the basin develops along the axis trending NW-SE direction and reveals a general symmetry of the bathymetry. And also the free-air gravity anomalies show a very similar pattern to the bathymetry of the basin. The sediment thickness is relatively thicker in the southeastern side of the basin than in the northwestern side. Although the crustal age of the Ulleung Basin is supposed to be younger than them of the Japan Basin and the Yamato Basin, the free-air gravity anomalies of the Ulleung Basin ranging -40 to 50 mGals are lower than the other basins, which suggests that the densities of crust and sediment of the Ulleng Basin are lower than the Japan Basin and the Yamato Basin.