• Journal of the Korean Society of Costume
• /
• v.56 no.9 s.109
• /
• pp.1-13
• /
• 2006

The purpose of this study is to apply a concept of open structure to clothing design and to verify the characteristics found in the various types of clothing which has open structure. The literatures from various academic fields including philosophy, literature, social science, architecture, and fine arts are investigated to define the concept of openness and to analyze it from the perspectives both of the visual and of the moaning of openness. This paper is to identify the types and the characteristics of clothing by future intention, complexity, discontinuity of open structure. By closely examining fashion design after 1980s found in fashion collection publications and designer's websites, the results of this study are as follows: first, the concept of openness can be classified into two different levels, that is, visual and meaning, secondly, in clothing the concept of open structure is applied to the meaning side by future intention, by complexity and by discontinuity. Open structure through future Intention has new content and interpretation and must have the possibility of intelligence awakening, future guidance and basic contents. Open structure through complexity has secondary function exists concurrent with the shape key example is the smart clothes with the digital functions. It has functions of amusement, supplement and protective, and is future clothes which satisfies with health, welfare, desire of beauty. Open structure with discontinuity is clothes with dramatic changes in system, structures and states. Structure can be changed by silhouette, detail, or fabric, material, or dramatic and practical function as tools in terms of productions and environment. This study can help to formulate and to integrate the concept of open structure in clothing with various phases and enhance the value of clothes by showing an application of the concept of openness to the clothing in meaning level.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.798-802
• /
• 2003

The robustness and reliability of vision algorithms is the key issue in robotic research and industrial applications. In this paper, the robust real time visual tracking in complex scene is considered. A common approach to increase robustness of a tracking system is to use different models (CAD model etc.) known a priori. Also fusion of multiple features facilitates robust detection and tracking of objects in scenes of realistic complexity. Because voting is a very simple or no model is needed for fusion, voting-based fusion of cues is applied. The approach for this algorithm is tested in a 3D Cartesian robot which tracks a toy vehicle moving along 3D rail, and the Kalman filter is used to estimate the motion parameters, namely the system state vector of moving object with unknown dynamics. Experimental results show that fusion of cues and motion estimation in a tracking system has a robust performance.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1055-1058
• /
• 2003

The robustness and reliability of vision algorithms is the key issue in robotic research and industrial applications. In this paper robust real time visual tracking in complex scene is considered. A common approach to increase robustness of a tracking system is the use of different model (CAD model etc.) known a priori. Also fusion or multiple features facilitates robust detection and tracking of objects in scenes of realistic complexity. Voting-based fusion of cues is adapted. In voting. a very simple or no model is used for fusion. The approach for this algorithm is tested in a 3D Cartesian robot which tracks a toy vehicle moving along 3D rail, and the Kalman filter is used to estimate the motion parameters. namely the system state vector of moving object with unknown dynamics. Experimental results show that fusion of cues and motion estimation in a tracking system has a robust performance.

• Journal of Information Processing Systems
• /
• v.9 no.4
• /
• pp.592-601
• /
• 2013

Object segmentation is a challenging task in image processing and computer vision. In this paper, we present a visual attention based segmentation method to segment small sized interesting objects in natural images. Different from the traditional methods, we first search the region of interest by using our novel saliency-based method, which is mainly based on band-pass filtering, to obtain the appropriate frequency. Secondly, we applied the Gaussian Mixture Model (GMM) to locate the object region. By incorporating the visual attention analysis into object segmentation, our proposed approach is able to narrow the search region for object segmentation, so that the accuracy is increased and the computational complexity is reduced. The experimental results indicate that our proposed approach is efficient for object segmentation in natural images, especially for small objects. Our proposed method significantly outperforms traditional GMM based segmentation.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.353-358
• /
• 2022

Due to the limited field of view of the pinhole camera, there is a lack of stability and accuracy in camera pose estimation applications such as visual SLAM. Nowadays, multiple-camera setups and large field of cameras are used to solve such issues. However, a multiple-camera system increases the computation complexity of the algorithm. Therefore, in multiple camera-assisted visual simultaneous localization and mapping (vSLAM) the multi-view tracking algorithm is proposed that can be used to balance the budget of the features in tracking and local mapping. The proposed algorithm is based on PanoSLAM architecture with a panoramic camera model. To avoid the scale issue 3D LiDAR is fused with omnidirectional camera setup. The depth is directly estimated from 3D LiDAR and the remaining features are triangulated from pose information. To validate the method, we collected a dataset from the outdoor environment and performed extensive experiments. The accuracy was measured by the absolute trajectory error which shows comparable robustness in various environments.

• Journal of KIISE:Software and Applications
• /
• v.31 no.12
• /
• pp.1621-1627
• /
• 2004

The decrease of visual quality at scene change occurs when the difference between the amount of target bits and actual coding is high. Especially, scene change at the P-Picture can lead to severely degrade visual qualities at itself and the pictures referencing it. In this paper, under the occurrence of scene change, we propose a new method, based on the analysis of existing inaccurate bits allocation, to improve the visual qualities of scene-changed and following pictures. The method allocates extra bits to scene-changed Picture and changes them upto the level of the complexity of intra picture. Also, the method changes target bits of following pictures upto the complexity of picture prior to the scene change. Computer simulation shows that the proposed method has improved 0.5-1.2dB higher than TM5 method in terms of PSNR.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.15 no.2
• /
• pp.91-100
• /
• 1987

Main purpose of this study is to test the usefulness of the SBE method in measuring ‘complexity’‘beauty’and ‘friendliness’other than ‘preference’. The study results are as follows. 1) The SBE results are as reliable and valid in measuring ‘complexity’‘beauty’and ‘friendliness’as in measuring ‘preference’. However, the degree of reliability and convergent validity can vary according to the inherent charateristics of those abstract quality themselves. 2) The correlation coefficients among the result of rating, SBE, frequency, and paired comparison methods are very high. 3) The perceived beauty of urban residential landscape reaches highest at the higher complexity level than that of the rural residential landscape.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.7
• /
• pp.332-338
• /
• 2001

A visually adaptive quantization method of DCT-based images based on Human Visual System(HVS) is proposed. This approach uses the spatial masking in HVS characteristics to obtain higher compression ratio with relatively small degradation in the image quality. HVS is nonsensitive to an edge area, so a high complexity area is quantized coarsely in contrast to fine quantization of the low complexity area. The complexity of an area is estimated by the variance of DCT coefficients of the image. Experimental results demonstrate the performance of the proposed method and the resulting images show little difference from the original image in the subjective perception.

• Korean Institute of Interior Design Journal
• /
• no.31
• /
• pp.56-63
• /
• 2002

This study intends to prepare a system that can be used, by applying digital technique, in analyzing complexity of architectural forms that have been visualized by the correlation based on the distribution chart made in accordance with profile lines. The profile lines are derived from the edge analysis of the architectural forms, simplified based on the visual theory. For the purpose, this study was conducted in the following ways: First, problems of the existing models for the elevation analysis were examined along with formal analysis based on visual recognition to consider the profile lines derived from the forms. Secondly, in elevation analysis, profile lines were derived by digital method to measure them qualitatively. To verify the objectivity of the measured data value, a survey was conducted based on the adjective cataloging method, and the correlation of the survey result and analyzed data was analyzed to verify the validity of the derived data. Thirdly, supplementation for the problems deducted from experiments and the possibility to use it in designing were suggested. Digital method has many advantages over the conventional analyzing system in deriving precise data value by excluding subjectivity. It also allows various analytical methods in analyzing numerous data repeatedly. Diversified models and methods of analysis considering numerous factors arising in the process of designing remain assignments to research in future.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1134-1139
• /
• 2019

One of the most important applications of computer vision algorithms is the detection of threat objects in x-ray security images. However, in the practical setting, this task is complicated by two properties inherent to the dataset, namely, the problem of class imbalance and visual complexity. In our previous work, we resolved the class imbalance problem by using a GAN-based anomaly detection to balance out the bias induced by training a classification model on a non-practical dataset. In this paper, we propose a new method to alleviate the visual complexity problem by using a KNN-based automatic cropping algorithm to remove distracting and irrelevant information from the x-ray images. We use the cropped images as inputs to our current model. Empirical results show substantial improvement to our model, e.g. about 3% in the practical dataset, thus further outperforming previous approaches, which is very critical for security-based applications.