• Journal of the Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.1-9
• /
• 2022

In this paper, we propose a vector-based augmentation technique that can generate data required for crack detection and a ConvNet(Convolutional Neural Network) technique that can learn it. Detecting cracks quickly and accurately is an important technology to prevent building collapse and fall accidents in advance. In order to solve this problem with artificial intelligence, it is essential to obtain a large amount of data, but it is difficult to obtain a large amount of crack data because the situation for obtaining an actual crack image is mostly dangerous. This problem of database construction can be alleviated with elastic distortion, which increases the amount of data by applying deformation to a specific artificial part. In this paper, the improved crack pattern results are modeled using ConvNet. Rather than elastic distortion, our method can obtain results similar to the actual crack pattern. By designing the crack data augmentation based on a vector, rather than the pixel unit used in general data augmentation, excellent results can be obtained in terms of the amount of crack change. As a result, in this paper, even though a small number of crack data were used as input, a crack database can be efficiently constructed by generating various crack directions and patterns.

• Geophysics and Geophysical Exploration
• /
• v.26 no.4
• /
• pp.211-228
• /
• 2023

Ground-penetrating radar (GPR) surveys are commonly used to monitor embankments, which is a nondestructive geophysical method. The results of GPR surveys can be complex, depending on the situation, and data processing and interpretation are subject to expert experiences, potentially resulting in false detection. Additionally, this process is time-intensive. Consequently, various studies have been undertaken to detect cavities in GPR survey data using deep learning methods. Deep-learning-based approaches require abundant data for training, but GPR field survey data are often scarce due to cost and other factors constaining field studies. Therefore, in this study, a deep- learning-based model was developed for embankment GPR survey cavity detection using data augmentation strategies. A dataset was constructed by collecting survey data over several years from the same embankment. A you look only once (YOLO) model, commonly used in computer vision for object detection, was employed for this purpose. By comparing and analyzing various strategies, the optimal data augmentation approach was determined. After initial model development, a stepwise process was employed, including box clustering, transfer learning, self-ensemble, and model ensemble techniques, to enhance the final model performance. The model performance was evaluated, with the results demonstrating its effectiveness in detecting cavities in embankment GPR survey data.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.11
• /
• pp.61-69
• /
• 2019

In this paper, we propose a multisensory(i.e., visual-auditory-tactile) based AR system for the education of cultural heritage. The proposed system provides a multisensory interaction by designing a user to experience with a 3D printed artifact which is mapped by a virtual 3D content of digital heritage. Compared with the existing systems of cultural heritage education based on augmented reality(AR) technology, this system focused on not only providing learning experience via a sense of visual and auditory, but also a sense of tactile. Furthermore, since this systems mainly provided the direct interactions using a 3D printed model, it gives a higher degree of realism than existing system that use touch or click motions on a 2D display of mobile phones and tablets. According to a result of user testing, we concluded that the proposed system delivered the excellent presence and learning flow to users. Particularly, from the usability evaluation, a 3D printed target artifact which is similar in shape to original heritage artifact, achieved the highest scores among the various tested targets.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.171-182
• /
• 2022

The safe use of a structure requires it to be maintained in an undamaged state. Thus, a typical factor that determines the safety of a structure is a crack in it. In addition, cracks are caused by various reasons, damage the structure in various ways, and exist in different shapes. Making matters worse, if these cracks are unattended, the risk of structural failure increases and proceeds to a catastrophe. Hence, recently, methods of checking structural damage using deep learning and computer vision technology have been introduced. These methods usually have the premise that there should be a large amount of training image data. However, the amount of training image data is always insufficient. Particularly, this insufficiency negatively affects the performance of deep learning crack detection algorithms. Hence, in this study, a method of augmenting crack image data based on the image translation technique was developed. In particular, this method obtained the crack image data for training a deep learning neural network model by transforming a specific case of a asphalt crack image into a concrete crack image or vice versa . Eventually, this method expected that a robust crack detection algorithm could be developed by increasing the diversity of its training data.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.493-496
• /
• 2009

Many AR (Augmented Reality) applications have been interested in a marker-less tracking since the tracking methods give camera poses without attaching explicit markers. In this paper, we propose a new marker-less page recognition and tracking algorithm for an AR book application such as DigilogBook. The proposed method only requires orthogonal images of pages, which need not to be trained for a long time, and the algorithm works in real-time. The page recognition is done in two steps by using SIFT (Scale Invariant Feature Transform) descriptors and the comparison evaluation function. And also, the method provides real-time tracking with 25fps ~ 30fps by separating the page recognition and the frame-to-frame matching into two multi-cores. The proposed algorithm will be extended to various AR applications that require multiple objects tracking.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.944-947
• /
• 2022

Due to the coronavirus pandemic, the wearing of a mask has been increasing worldwide; thus, the importance of image analysis on masked face images has become essential. Although head pose estimation can be applied to various face-related applications including driver attention, face frontalization, and gaze detection, few studies have been conducted to address the performance degradation caused by masked faces. This study proposes a new data augmentation that synthesizes the masked face, depending on the face image size and poses, which shows robust performance on BIWI benchmark dataset regardless of mask-wearing. Since the proposed scheme is not limited to the specific model, it can be utilized in various head pose estimation models.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.311-312
• /
• 2022

본 논문에서는 딥러닝 기반 욕창 감지를 위한 욕창 객체 탐지를 연구한다. 객체 탐지 딥러닝 기법으로 RCNN, Fast R-CNN, Faster R-CNN, YOLO 등 다양한 기법이 존재하며, 각 모델의 특징 또한 다르다. 욕창은 단계별로 피부, 조직에 손상의 정도가 다르다. 낮은 단계의 경우 일반적인 피부색과 유사하게 나타나며, 높은 단계의 경우 근육, 뼈, 지지 조직 등의 괴사로 인해 삼출물 또는 괴사조직이 나타난다. 논문에서는 One-Stage Detection 기법인 YOLO를 기반으로 욕창 이미지 내부에서 욕창 탐지를 진행한다. 현재 보유하고 있는 이미지 데이터 수가 많지 않아 데이터 증강기법을 통해 데이터를 증강하여 학습에 활용하였다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.346-351
• /
• 2023

오픈 도메인 대화 시스템은 산업에서 다양하게 활용될 수 있지만 유해한 응답을 출력할 수 있다는 위험성이 지적되어 왔다. 본 논문에서는 언급된 위험성을 완화하기 위해 데이터 측면에서 대화 시스템 모델을 개선하는 방법을 제안한다. 대화 모델의 유해한 응답을 유도하도록 설계된 데이터셋을 사용하여 모델이 올바르지 못한 응답을 생성하게 만들고, 이를 LLM을 활용하여 안전한 응답으로 수정한다. 또한 LLM이 정확하게 수정하지 못하는 경우를 고려하여 추가적인 필터링 작업으로 데이터셋을 보완한다. 생성된 데이터셋으로 추가 학습된 대화 모델은 기존 대화 모델에 비해 대화 일관성 및 유해성 면에서 성능이 향상되었음을 확인했다.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.2078-2079
• /
• 2009

This research suggests the framework for human body learning system using various forms of bidirectional interfaces. The existing systems mostly use the limited and unidirectional methods which are merely focused on the visual information. Our system provides more realistic visual information using 3D organ models from the real human body. Also we combine the haptic and augmented reality techniques into our system for wider range of interaction means. Through this research, we aim to overcome the limitation of existing science education systems and explore the effective scheme to fuse the real and virtual educational environment into one.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.1019-1022
• /
• 2005

멀티미디어 콘텐츠에 대한 처리기술과 사용자 인터페이스의 발전으로 인해, 교육 현장에서 광범위하게 사용되는 교육 도구로 e-러닝이 자리 잡고 있다. 현재까지 연구되어온 교육 콘텐츠는 단순한 상호작용만을 허용하고, 실습형 인터페이스를 제공하기에는 제약이 따르며, 기존의 콘텐츠를 재구성하여 개발하기에는 많은 비용과 시간이 소요된다. 그리고 학습효과 측정에 대한 의식이 희박하고, 콘텐츠 평가의 명확한 기준이 없어 품질 향상에 많은 어려움이 뒤따른다. 이를 개선하기 위해 본 논문에서는 멀티미디어를 이용한 자기주도적 학습 콘텐츠를 제작한다. 이렇게 제작된 교육 콘텐츠를 비전 기반의 증강현실을 이용하여 더욱더 직관적이고, 인터랙티브한 교육 콘텐츠를 제공한다.