• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권5호
• /
• pp.2253-2272
• /
• 2018

We propose a deep learning method for multi-focus image fusion. Unlike most existing pixel-level fusion methods, either in spatial domain or in transform domain, our method directly learns an end-to-end fully convolutional two-stream network. The framework maps a pair of different focus images to a clean version, with a chain of convolutional layers, fusion layer and deconvolutional layers. Our deep fusion model has advantages of efficiency and robustness, yet demonstrates state-of-art fusion quality. We explore different parameter settings to achieve trade-offs between performance and speed. Moreover, the experiment results on our training dataset show that our network can achieve good performance with subjective visual perception and objective assessment metrics.

• 한국위성정보통신학회논문지
• /
• 제12권3호
• /
• pp.15-21
• /
• 2017

2012년 5월 다목적실용위성 KOMPSAT-3 발사 성공 이후, 2013년 8월 KOMPSAT-5, 2015년 3월 KOMPSAT-3A의 발사 성공으로 국내는 광학, 레이더, 열적외선 센서를 통합 운영할 수 있게 되었으며, 각 센서들의 특성을 융합 활용할 수 있는 기반을 마련하였다. 단일 센서가 가지고 있는 활용의 적용 범위나 산출물 정확도에 한계점을 극복하고자 다중 센서들의 장점을 취하고 단점은 상호 보완하는 다종센서간 영상융합기술이 대두하게 되었다. 본 논문에서는 다목적실용위성 군을 활용한 영상 융합 및 고부가 산출물 생성을 위한 소프트웨어(InFusion) 개발에 대하여 소개하고자 한다. 먼저 각 센서들의 특징 설명과 융합 소프트웨어 개발의 필요성에 대하여 기술하고, 개발 전과정에 대하여 상세히 설명하고자 한다. 국내외 다목적실용위성 군의 자료 활용성을 증대시키고 고부가 제품생성을 통한 국내 소프트웨어의 우수성을 알리는 계기가 되고자 한다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1334-1336
• /
• 2003

On the basis of comprehensive analysis and summarization of the image fusion algorithms provided by PCI Geomatica software, deficiencies in image fusion processing functions of this software are put forwarded in this paper. This limitation could be improved by further developing PCI Geomatica on the user’ side. Five effective algorithms could be added into PCI Geomatica. In this paper, the detailed description of how to customize and further develop PCI Geomatica by using Microsoft Visual C++ 6.0, PCI SDK Kit and GDB technique is also given. Through this way, the remote sensing imagery fusion functions of PCI Geomatica software can be extended.

• 한국우주과학회:학술대회논문집(한국우주과학회보)
• /
• 한국우주과학회 2000년도 한국우주과학회보 제9권1호
• /
• pp.34-34
• /
• 2000

No Abstract, See Full Text

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.88-97
• /
• 2023

Traffic flow prediction is of great significance in urban planning and traffic management. As the complexity of urban traffic increases, existing prediction methods still face challenges, especially for the fusion of spatiotemporal information and the capture of long-term dependencies. This study aims to use the fusion model of graph neural network to solve the spatio-temporal information fusion problem in traffic flow prediction. We propose a new deep learning model Spatio-Temporal Information Fusion using Graph Neural Networks (STFGNN). We use GCN module, TCN module and LSTM module alternately to carry out spatiotemporal information fusion. GCN and multi-core TCN capture the temporal and spatial dependencies of traffic flow respectively, and LSTM connects multiple fusion modules to carry out spatiotemporal information fusion. In the experimental evaluation of real traffic flow data, STFGNN showed better performance than other models.

• 대한핵의학회:학술대회논문집
• /
• 대한핵의학회 2003년도 제25차 연수교육
• /
• pp.47-47
• /
• 2003

• ETRI Journal
• /
• 제35권5호
• /
• pp.923-926
• /
• 2013

To resolve video enhancement problems, a novel method of gradient domain fusion wherein gradient domain frames of the background in daytime video are fused with nighttime video frames is proposed. To verify the superiority of the proposed method, it is compared to conventional techniques. The implemented output of our method is shown to offer enhanced visual quality.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권1호
• /
• pp.196-212
• /
• 2014

Facial expression recognition is an important part in emotional interaction between human and machine. This paper proposes a facial expression recognition approach based on multi-classifier fusion with stacking algorithm. The kappa-error diagram is employed in base-level classifiers selection, which gains insights about which individual classifier has the better recognition performance and how diverse among them to help improve the recognition accuracy rate by fusing the complementary functions. In order to avoid the influence of the chance factor caused by guessing in algorithm evaluation and get more reliable awareness of algorithm performance, kappa and informedness besides accuracy are utilized as measure criteria in the comparison experiments. To verify the effectiveness of our approach, two public databases are used in the experiments. The experiment results show that compared with individual classifier and two other typical ensemble methods, our proposed stacked ensemble system does recognize facial expression more accurately with less standard deviation. It overcomes the individual classifier's bias and achieves more reliable recognition results.

• 기술혁신학회지
• /
• 제3권2호
• /
• pp.78-93
• /
• 2000

Since computerized numerical controller(CNC) emerged as a result of the fusion of the electronics technology and the mechanical technology, there has been continuous evolution of CNC technology in the mechatronics industry. The industry is recently developing a new control system based on the fusion of personal computer(PC) and CNC. Upgraded PC has now integrated into CNC, making various machines possible to exchange data, software and hardware, and to greatly improve man-machine interface. The fusion of PC and CNC can form a new paradigm in technological innovation of not only control system but also whole machinery industry in near the future. Korea lagged behind the developed countries in the development of open control system with the fusion of PC. Turbotek, Hyundai Motor and Daewoo are leading companies, but their commercial possibility seems to be low because domestic market is too small to reap a commercial benefit. Nevertheless, the development of the system is an essential step for Korea to embark on a future technological paradigm of the machinery industry. The government needs to play some role for the development, for instance, government R&D projects, institutional building and training of related technicians.

• Journal of Information Processing Systems
• /
• 제12권1호
• /
• pp.35-45
• /
• 2016

To resolve the problems of Poisson/impulse noise, blurriness, and sharpness in degraded X-ray images, a novel and efficient enhancement algorithm based on X-ray image fusion using a discrete wavelet transform is proposed in this paper. The proposed algorithm consists of two basics. First, it applies the techniques of boundary division to detect Poisson and impulse noise corrupted pixels and then uses the Wiener filter approach to restore those corrupted pixels. Second, it applies the sharpening technique to the same degraded X-ray image. Thus, it has two source X-ray images, which individually preserve the enhancement effects. The details and approximations of these sources X-ray images are fused via different fusion rules in the wavelet domain. The results of the experiment show that the proposed algorithm successfully combines the merits of the Wiener filter and sharpening and achieves a significant proficiency in the enhancement of degraded X-ray images exhibiting Poisson noise, blurriness, and edge details.