• ICROS
• /
• v.21 no.4
• /
• pp.27-33
• /
• 2015

단일 센서 기반의 표적 탐지 문제에서 센서의 한계 요소에 의해 탐지 성능이 제한된다. 따라서, 최근 단일 센서 기반의 표적 탐지 성능을 향상시키기 위한 방안으로 각 센서의 강점을 효과적으로 융합하는 다중 센서 정보 융합 기반의 표적 탐지 기법에 대한 연구가 활발히 진행되고 있다. 센서 정보 융합을 위해서는 각 센서별 영상 획득, 각 영상의 기하학적 정합, 센서 정보 융합 기반의 표적 탐지 기술이 필요하며, 본 논문에서는 이에 대한 기술 및 개발 동향을 소개한다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.142-149
• /
• 2015

Most of the mono-camera based lane detection systems are fragile on poor illumination conditions. In order to compensate limitations of single sensor utilization, lane information fusion system using multiple lane sensors is an alternative to stabilize performance and guarantee high precision. However, conventional fusion schemes, which only concerns object detection, are inappropriate to apply to the lane information fusion. Even few studies considering lane information fusion have dealt with limited aids on back-up sensor or omitted cases of asynchronous multi-rate and coverage. In this paper, we propose a lane information fusion scheme utilizing multiple lane sensors with different coverage and cycle. The precise lane information fusion is achieved by the proposed fusion framework which considers individual ranging capability and processing time of diverse types of lane sensors. In addition, a novel lane estimation model is proposed to synchronize multi-rate sensors precisely by up-sampling spare lane information signals. Through quantitative vehicle-level experiments with around view monitoring system and frontal camera system, we demonstrate the robustness of the proposed lane fusion scheme.

• Korean Journal of Remote Sensing
• /
• v.20 no.4
• /
• pp.275-288
• /
• 2004

This paper presents a fuzzy relaxation labeling approach incorporated to the fuzzy logic fusion scheme for the classification of multi-sensor remote sensing images. The fuzzy logic fusion and iterative relaxation labeling techniques are adopted to effectively integrate multi-sensor remote sensing images and to incorporate spatial neighboring information into spectral information for contextual classification, respectively. Especially, the iterative relaxation labeling approach can provide additional information that depicts spatial distributions of pixels updated by spatial information. Experimental results for supervised land-cover classification using optical and multi-frequency/polarization images indicate that the use of multi-sensor images and spatial information can improve the classification accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.7
• /
• pp.1202-1208
• /
• 2008

This paper represents the multiple sensor fusion algorithm for the deep-sea unmanned underwater vehicles (UUV), composed of a remotely operated vehicle (ROV) 'Hemire' and a depressor 'Henuvy'. The performance of underwater positioning system usually highly depend on that of acoustic sensors such as ultra short base line(USBL), long base line(LBL) and altimeter. A practical sensor fusion algorithm is proposed in the sense of a moving window concept. The performance of the proposed algorithm can be observed by applying the algorithm to the Hemire sea trial data which was measured at the East Sea.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.2
• /
• pp.178-185
• /
• 2011

In this paper, we propose the position estimation algorithm based on the multisensor fusion using equalization of state variables and feedback structure. First, the state variables measured from INS of main sensor with large error and DVL of assistance sensor with small error are measured before prediction phase. Next, the equalized state variables are entered to each filter and fused the enhanced state variables for prediction and update phases. Finally, the fused state variables are returned to the main sensor for improving the position estimation of UUV. For evaluation, we create the moving course of UUV by simulation and confirm the performance of position estimation by applying the proposed algorithm. The evaluation results show that the proposed algorithm is the best for position estimation and also possible for robust position estimation at the change period of moving courses.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.1
• /
• pp.75-86
• /
• 2012

Synthetic Aperture Radar(SAR) imaging system is independent of solar illumination and weather conditions; however, SAR image is difficult to interpret as compared with optical images. It has been increased interest in multi-sensor fusion technique which can improve the interpretability of $SAR^{\circ\circ}$ images by fusing the spectral information from multispectral(MS) image. In this paper, a multi-sensor fusion method based on high-frequency extraction process using Fast Fourier Transform(FFT) and outlier elimination process is proposed, which maintain the spectral content of the original MS image while retaining the spatial detail of the high-resolution SAR image. We used TerraSAR-X which is constructed on the same X-band SAR system as KOMPSAT-5 and KOMPSAT-2 MS image as the test data set to evaluate the proposed method. In order to evaluate the efficiency of the proposed method, the fusion result was compared visually and quantitatively with the result obtained using existing fusion algorithms. The evaluation results showed that the proposed image fusion method achieved successful results in the fusion of SAR and MS image compared with the existing fusion algorithms.

• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.4
• /
• pp.39-46
• /
• 2008

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.1008-1013
• /
• 1992

본 논문에서는 다중 로보느의 협조제어(Coordinated Control)를 위한 로보트 콘트롤러의 설계에 대해서 연구한다. 첫 부분에서는 다중 로보느의 연구배경 및 연구동기에 대해서 논의하고 이어서 Coordinated Task를 묘사하기 위한 Programming Primiitive Set을 정의하며 구현에 대해서도 논의한다. 특히 Motopn Primitive는 synchronous(Coordinated Motion), Asynchronous Motion, Conditional Motion, 특수 Motion으로 분류하고, 각각의 궤적계획 및 구현에 대해서도 간단히 논의한다. 특히 본 논문에서는 외부의 변화하는 환경에 효과적으로 적응할 수 있게 하기 위하여 Vision센서, Encoder신호와 Limit센서, Force센서 등의 다양한 외부 센서를 융합 처리할수 있는 다중 로보트 제어 시스템을 개발하였다.

• Korean Journal of Remote Sensing
• /
• v.19 no.4
• /
• pp.329-339
• /
• 2003

In this study, an approach of image fusion in decision level has been proposed for unsupervised image classification using the images acquired from multiple sensors with different characteristics. The proposed method applies separately for each sensor the unsupervised image classification scheme based on spatial region growing segmentation, which makes use of hierarchical clustering, and computes iteratively the maximum likelihood estimates of fuzzy class vectors for the segmented regions by EM(expected maximization) algorithm. The fuzzy class vector is considered as an indicator vector whose elements represent the probabilities that the region belongs to the classes existed. Then, it combines the classification results of each sensor using the fuzzy class vectors. This approach does not require such a high precision in spatial coregistration between the images of different sensors as the image fusion scheme of pixel level does. In this study, the proposed method has been applied to multispectral SPOT and AIRSAR data observed over north-eastern area of Jeollabuk-do, and the experimental results show that it provides more correct information for the classification than the scheme using an augmented vector technique, which is the most conventional approach of image fusion in pixel level.

• Proceedings of the KIEE Conference
• /
• 2007.07a
• /
• pp.1787-1788
• /
• 2007

최근 장애물 감지, 경로 생성 등 많은 분야에서 여러 종류의 센서를 사용한 연구가 많이 진행되고 있다. 다중의 센서를 이용하면 개별 센서를 사용한 경우보다 정밀한 데이터의 측정이 가능하다. 이 논문에서는 효율적인 장애물 인식이나, 경로 생성을 위해 다중 센서로부터 측정된 데이터를 융합시키는 알고리즘을 제안하였고, 모의실험을 통해서는 이동 로봇의 기본 경로에 장애물이 존재한 상황에서 하나의 센서를 사용한 경우보다 최적화된 경로를 얻을 수 있다.