• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2005.11a
• /
• pp.59-80
• /
• 2005

This Paper Presents a Rational Function Model (RFM)-based image matching technique for IKONOS satellite imagery. This algorithm adopts the object-space approach and reduces the search space within the confined line-shaped area called the Piecewise Matching Line (PLM). Also, the detailed procedure of generating 3-D surface information using the Rational Function model Coefficients (RFCs) is introduced as an end-user point of view. As a result, the final generated Digital Elevation Model (DEM) using the proposed scheme shows a mean error of 2$\cdot$2 m and RMSE of 3$\cdot$8 m compared with that from 1:5000 digital map.

• ETRI Journal
• /
• v.33 no.2
• /
• pp.240-250
• /
• 2011

To enable a relevance feedback paradigm to evolve itself by users' feedback, a reinforcement learning method is proposed. The feature space of the medical images is partitioned into positive and negative hypercubes by the system. Each hypercube constitutes an individual in a genetic algorithm infrastructure. The rules take recombination and mutation operators to make new rules for better exploring the feature space. The effectiveness of the rules is checked by a scoring method by which the ineffective rules will be omitted gradually and the effective ones survive. Our experiments on a set of 10,004 images from the IRMA database show that the proposed approach can better describe the semantic content of images for image retrieval with respect to other existing approaches in the literature.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.5
• /
• pp.505-510
• /
• 2009

In recent years the space where a robot works has been expanding to the human space unlike traditional industrial robots that work only at fixed positions apart from humans. A human in the recent situation may be the owner of a robot or the target in a robotic application. This paper deals with the latter case; when a robot vision system is employed to monitor humans for a surveillance application, each person in a scene needs to be identified. Humans, however, often move together, and occlusions between them occur frequently. Although this problem has not been seriously tackled in relevant literature, it brings difficulty into later image analysis steps such as tracking and scene understanding. In this paper, a probabilistic neural network is employed to learn the patterns of the best dividing position along the top pixels of an image region of partly occlude people. As this method uses only shape information from an image, it is simple and can be implemented in real time.

• Korean Institute of Interior Design Journal
• /
• no.9
• /
• pp.116-126
• /
• 1996

Modern society has achieved rapid growth in economy and materials whereas it caused such problems as municipal extension and high density of population, Due to rapid change of social environment, it became more complicated and multifarious than ever it before. Helping the people all kinds of routine affairs police box is giving a negative image to the citizens, for its environment doesn't have got rid of its old fashion . It's being an unharmonious factor to its surroundings, a solution is needed. So, this study is focused on recognizing the change of value system with the flow of time, planning a new image of police box for the change and in consequence recovering the trustworthy between people and the nation. For this , by grasping the characteristics of each space and through space-dividing and design corresponding to it, the plan is provided to make a pleasant interior environment of police box and to make it a symbol of local society. As a result of this study, we will have the police box not only as an office providing the locals with security and service but also as eyes of the country which watches the municipal environment.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.591-593
• /
• 2003

The study demonstrates the data extraction capabilities from the simulated ROCSAT-2 image by manual delineation. The GIS data are able to identify as fifteen categories of the classes I & II for the simulated ROCSAT-2 and SPOT image data. The areas of the paddy are identified almost the same results for both cases, but the arid farmland are identified differently about 30%. The ROCSAT-2 case can be also identified as seven more categories of the class III, but SPOT-4 case cannot.

• Journal of Sensor Science and Technology
• /
• v.30 no.5
• /
• pp.290-294
• /
• 2021

Experts have designed popular and successful model architectures, which, however, were not the optimal option for different scenarios. Despite the remarkable performances achieved by deep neural networks, manually designed networks for classification tasks are the backbone of object detection. One major challenge is the ImageNet pre-training of the search space representation; moreover, the searched network incurs huge computational cost. Therefore, to overcome the obstacle of the pre-training process, we introduce a network adaptation technique using a pre-trained backbone model tested on ImageNet. The adaptation method can efficiently adapt the manually designed network on ImageNet to the new object-detection task. Neural architecture search (NAS) is adopted to adapt the architecture of the network. The adaptation is conducted on the MobileNetV2 network. The proposed NAS is tested using SSDLite detector. The results demonstrate increased performance compared to existing network architecture in terms of search cost, total number of adder arithmetics (Madds), and mean Average Precision(mAP). The total computational cost of the proposed NAS is much less than that of the State Of The Art (SOTA) NAS method.

• Journal of the Korean Mathematical Society
• /
• v.59 no.1
• /
• pp.105-127
• /
• 2022

It is known that the maximal invariant set of a continuous iterative dynamical system in a compact Hausdorff space is equal to the intersection of its forward image sets, which we will call the first minimal image set. In this article, we investigate the corresponding relation for a class of discontinuous self maps that are on the verge of continuity, or topologically almost continuous endomorphisms. We prove that the iterative dynamics of a topologically almost continuous endomorphisms yields a chain of minimal image sets that attains a unique transfinite length, which we call the maximal invariance order, as it stabilizes itself at the maximal invariant set. We prove the converse, too. Given ordinal number ξ, there exists a topologically almost continuous endomorphism f on a compact Hausdorff space X with the maximal invariance order ξ. We also discuss some further results regarding the maximal invariance order as more layers of topological restrictions are added.

• Korean Institute of Interior Design Journal
• /
• no.25
• /
• pp.149-154
• /
• 2000

The concept of "place" has recently been given much attention by those who discuss problems of urban design and architecture. And we used the term "existential space" denote our concept or image of the environment. To create new space means to implement existential patterns in a given environment. So, this thesis explores the spatial meaning of correlation in Heideggers Existential Space and Situation of Fengshui.tuation of Fengshui.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1899-1902
• /
• 2003

Recently several methods have been developed for the virtual space construction. Generally, most of the methods are geometric-based rendering technic, but they are difficult to construct real-time rendering because of large data. In this paper, we present a three dimension image-based rendering method that enable a constant speed of real-time rendering regardless of object complexity in virtual space. The Proposed method shows good performance for the virtual space construction with high complexity.

• Proceedings of the Korean Institute of Interior Design Conference
• /
• 2005.10a
• /
• pp.165-170
• /
• 2005

It is important factor; understand definition and concept, grasp application method and property about transparency for expression of skin in design of retail space. This research do target; clarify the feature of transparency for expression of skin in modern retail space, and it is based in these viewpoint that analyze the feature through an experiment of image estimation(SD method) into object to modern retail space that express transparency of skin.