• 패션비즈니스
• /
• 제22권1호
• /
• pp.114-123
• /
• 2018

The purpose of this study is to investigate the visual elements for effectively conveying the make-up method of the Korean history. We will do basic research on language visualization through visual poetry by using a make-up method as a visual expression element. Our research methods consisted of a related literature research, an internet search, and case study methods. The make-up methods of Korean classical make-up through visual poetry consisted of a through literature review. First, make-up methods, cosmetics, jewelry, and hair styles are shown in the classic make-up style of each age. Second, classical make-up visual poetry shows the identity, gender, and character depictions. Third, there were many visual metaphors about the hair types, figures, and hair among the classical make-up methods of each age. I think that this topic is worth researching as an appropriate medium to increase attractiveness. This research is with visual expression elements of the Korea make-up method. This study analyzed the Korean traditional make-up method that expresses and reinterprets visual metaphors. The results of this study can be applied for basic research.

• 한국멀티미디어학회논문지
• /
• 제24권7호
• /
• pp.880-889
• /
• 2021

In everyday life, recognizing people's emotions from their frames is essential and is a popular research domain in the area of computer vision. Visual emotion has a severe class imbalance in which most of the data are distributed in specific categories. The existing methods do not consider class imbalance and used accuracy as the performance metric, which is not suitable for evaluating the performance of the imbalanced dataset. Therefore, we proposed a method for recognizing visual emotion using balanced data augmentation to address the class imbalance. The proposed method generates a balanced dataset by adopting the random over-sampling and image transformation methods. Also, the proposed method uses the Focal loss as a loss function, which can mitigate the class imbalance by down weighting the well-classified samples. EfficientNet, which is the state-of-the-art method for image classification is used to recognize visual emotion. We compare the performance of the proposed method with that of conventional methods by using a public dataset. The experimental results show that the proposed method increases the F1 score by 40% compared with the method without data augmentation, mitigating class imbalance without loss of classification accuracy.

• 로봇학회논문지
• /
• 제17권3호
• /
• pp.334-338
• /
• 2022

In visual simultaneous localization and mapping (vSLAM), the correct recognition of a place benefits in relocalization and improved map accuracy. However, its performance is significantly affected by the environmental conditions such as variation in light, viewpoints, seasons, and presence of dynamic objects. This research addresses the problem of feature occlusion caused by interference of dynamic objects leading to the poor performance of visual place recognition algorithm. To overcome the aforementioned problem, this research analyzes the role of scene semantics in correct detection of a place in challenging environments and presents a semantics aided visual place recognition method. Semantics being invariant to viewpoint changes and dynamic environment can improve the overall performance of the place matching method. The proposed method is evaluated on the two benchmark datasets with dynamic environment and seasonal changes. Experimental results show the improved performance of the visual place recognition method for vSLAM.

• ETRI Journal
• /
• 제45권5호
• /
• pp.795-810
• /
• 2023

Unmanned aerial vehicles (UAV) and ground vehicles (UGV) require advanced video analytics for various tasks, such as moving object detection and segmentation; this has led to increasing demands for these methods. We propose a zero-shot video object segmentation method specifically designed for UAV and UGV applications that focuses on the discovery of moving objects in challenging scenarios. This method employs a background memory model that enables training from sparse annotations along the time axis, utilizing temporal modeling of the background to detect moving objects effectively. The proposed method addresses the limitations of the existing state-of-the-art methods for detecting salient objects within images, regardless of their movements. In particular, our method achieved mean J and F values of 82.7 and 81.2 on the DAVIS'16, respectively. We also conducted extensive ablation studies that highlighted the contributions of various input compositions and combinations of datasets used for training. In future developments, we will integrate the proposed method with additional systems, such as tracking and obstacle avoidance functionalities.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.283-292
• /
• 2019

This paper introduces the development and current prosperity of the branch discipline of visual anthropology and describes the status and current situation of modern visual anthropology and analyzes the rationality that the achievements of visual anthropology is viewed as texts and enjoy the same achievements, making it more basis and scientific in the selection of visual anthropology in subsequent research. This article comprehensively uses Delphi method and analytic hierarchy process to construct an evaluation system of visual anthropology, as well as put forward the basic principles of screening films using this evaluation system in subsequent studies and a simple outlook for future expansion.

• 대한인간공학회지
• /
• 제31권6호
• /
• pp.705-713
• /
• 2012

Objective: The aim of this study is to predict human visual target search using ACT-R cognitive architecture in real scene images. Background: Human uses both the method of bottom-up and top-down process at the same time using characteristics of image itself and knowledge about images. Modeling of human visual search also needs to include both processes. Method: In this study, visual target object search performance in real scene images was analyzed comparing experimental data and result of ACT-R model. 10 students participated in this experiment and the model was simulated ten times. This experiment was conducted in two conditions, indoor images and outdoor images. The ACT-R model considering the first saccade region through calculating the saliency map and spatial layout was established. Proposed model in this study used the guide of visual search and adopted visual search strategies according to the guide. Results: In the analysis results, no significant difference on performance time between model prediction and empirical data was found. Conclusion: The proposed ACT-R model is able to predict the human visual search process in real scene images using salience map and spatial layout. Application: This study is useful in conducting model-based evaluation in visual search, particularly in real images. Also, this study is able to adopt in diverse image processing program such as helper of the visually impaired.

• 한국산업융합학회 논문집
• /
• 제18권2호
• /
• pp.90-98
• /
• 2015

This research propose with image-based visual a new approach to design a feedback control of mobile robot. because mobile robot must be recharged periodically, it is necessary to detect and move to docking station. Generally, laser scanner is used for detect of position of docking station. CCD Camera is also used for this purpose. In case of using camera, the position-based visual servoing method is widely used. But position-based visual servoing method requires the accurate calibration and it is hard and complex work. Another method using cameras is inmage-based visual feedback. Recently, image based visual feedback is widely used for robotic application. But it has a problem that cannot have linear trajectory in the 3-dimensional space. Because of this weak point, image-based visual servoing has a limit for real application. in case of 2-dimensional movement on the plane, it has also similar problem. In order to solve this problem, we point out the main reason of the problem of the resolved rate control method that has been generally used in the image-based visual servoing and we propose an image-based visual feedback method that can reduce the curved trajectory of mobile robot in th cartesian space.

• Architectural research
• /
• 제15권2호
• /
• pp.87-94
• /
• 2013

Throughout the history of architecture, sometimes the main focus of design was determined by a particular visual representation method, and other times a particular form of visual representation method was required by perception of a particular architectural issue or an architectural form or idea. That is why the visual representation method of architects becomes an important means of reading the flow of idea and thinking behind architecture. This study is an investigation on the relation between architectural thinking and visual representation method expressed through the conceptual drawings by avant-garde architects of the 1970s and 80s, a period of the emergence of postmodernism. Rather than proving the objective reality regarded important by traditional architectural drawing, attempts are made to express the design concept in which the project has its base. Such interpretation and explanation regarding the concept become the main interest of the drawing. It is not that the architecture itself was not expressed in the contents, but it may not be the main subject of expression in the drawing. The value of architectural drawing recovers its value as an art work in itself, as a means of communication, and as an important conceptual tool in the design process. It can be seen that the visual representation method in postmodern architectural drawings is breaking free of the traditional objective depiction of matter and is changing and developing as a design tool of the architect.

• 감성과학
• /
• 제11권3호
• /
• pp.339-356
• /
• 2008

The purpose of this research was to identify the difference between expected and actual corporate image in the market and to verify the possibility of green-oriented corporate identity (CI) visual design as a useful method for communicating with consumers. In addition, this research suggests how green-oriented CI visual design can effectively convey corporate image to consumers. The methods of research used to achieve this aim were case studies and questionnaire surveys. In regard to the results, the difference between consumers'perceived favourable corporate image and companies' expectation about corporate image was found. Moreover, the results show that green-oriented visual identity (VI) design can improve corporate image. In turn, the gap between the expected and actual perception of corporate image can be decreased through green-oriented design. Based on these results, a method of effective development for green-oriented VI design is recommended.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.279-280
• /
• 2006

This paper describes a method for reconstructing 3D feet in a real time vision based marker free motion capture system. The proposed method is developed based on the visual hull and model fitting. For a real time computing, a special lookup table is employed in this paper. This method is implemented and tested using three CCD cameras and preliminary results are presented in this paper.