• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.893-903
• /
• 2022

Recently, computer vision (CV)-based safety monitoring (i.e., object detection) system has been widely researched in the construction industry. Sufficient and high-quality data collection is required to detect objects accurately. Such data collection is significant for detecting small objects or images from different camera angles. Although several previous studies proposed novel data augmentation and synthetic data generation approaches, it is still not thoroughly addressed (i.e., limited accuracy) in the dynamic construction work environment. In this study, we proposed a game engine-driven synthetic data generation model to enhance the accuracy of the CV-based object detection model, mainly targeting small objects. In the virtual 3D environment, we generated synthetic data to complement training images by altering the virtual camera angles. The main contribution of this paper is to confirm whether synthetic data generated in the game engine can improve the accuracy of the CV-based object detection model.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.33 no.5
• /
• pp.511-517
• /
• 2007

Purpose: The aim of this study is to determine whether a difference in the amount of bone graft material is needed between edentulous patients and dentulous patients and to calculate the amount of augmentation for a sinus lift procedure. Methods: 19 patients(20 sinuses) were included to measure maxillary sinus volume. Facial CT scanning was performed using MX 8000 IDT CT devices(Philips, USA). And it was used for IDLvm(The IDL Virtual Machine) 6.0, CT Volume Analyzer Ver 2.3 program to measure maxillary sinus volumes Results: At edentulous patients, volumes(mean${\pm}SD$) of the inferior portion of the sinuses were $0.56{\pm}0.13cm^3$(5mm height), $2.35{\pm}0.57cm^3$(10mm height), $4.85{\pm}1.10cm^3$(15mm height). At dentulous patients, volumes(mean${\pm}SD$) of the inferior portion of the sinuses were $0.41{\pm}0.18cm^3$(5mm height), $1.76{\pm}0.42cm^3$(10mm height), $3.80{\pm}0.84cm^3$ (15mm height). A significant correlation was found between augmentation height(5mm, 10mm, 15mm) and the calculated sinus volume.(p=0.027, p=0.018, p=0.044) Conclusions: A significant correlation was found between augmentation height(5mm, 10mm, 15mm) and the calculated sinus volume. Detailed preoperative knowledge of sinus lift augmentation volume is helpful in determining the appropriate amount of the bone graft material.

• The KIPS Transactions:PartB
• /
• v.13B no.5 s.108
• /
• pp.499-506
• /
• 2006

This Paper describes a fast and stable camera pose estimation method for real-time augmented reality systems. From the feature tracking results of a marker on a single frame, we estimate the camera rotation matrix and the translation vector. For the camera pose estimation, we use the shape factorization method based on the scaled orthographic Projection model. In the scaled orthographic factorization method, all feature points of an object are assumed roughly at the same distance from the camera, which means the selected reference point and the object shape affect the accuracy of the estimation. This paper proposes a flexible and stable selection method for the reference point. Based on the proposed method, we implemented a video augmentation system that inserts virtual 3D objects into the input video frames. Experimental results showed that the proposed camera pose estimation method is fast and robust relative to the previous methods and it is applicable to various augmented reality applications.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1224-1235
• /
• 2017

Recently, augmented reality technology has received much attention in many fields. This paper presents an augmented reality system using Rubiks' Cube which can augment various 3D objects depending on patterns of a Rubiks' cube. The system first detects a cube from an image using partitional clustering and strongly connected graph. Thereafter, the system detects the top side of the cube and finds a proper pattern to determine which object should be augmented. An object corresponding to the pattern is finally augmented according to the camera viewpoint. Experimental results show that the proposed system successfully augments various virtual objects in real time.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06b
• /
• pp.212-215
• /
• 2010

본 논문은 카메라 영상을 통해 사용자의 손동작을 인식하여 가상의 물체를 증강시키는 인터페이스를 제안한다. 사용자는 영상의 일부를 원형으로 그려주는 특정한 손동작을 취하여 영역을 선택하고 시스템은 이를 인식하여 물체를 증강 시킨다. 손동작을 인식하기 위하여 먼저 손 외곽선을 찾아낸 후, 찾아낸 외곽선의 곡률을 계산하여 손가락의 위치를 알아낸다. 알아낸 손가락의 상대적인 위치와 개수를 이용하여 손동작을 구분한다. 또한 적은 연산량으로도 안정적으로 물체를 증강 시킬 수 있도록 이전 프레임에서 자세추정에 사용된 특징점들을 이용하여 현재 프레임에서 필요한 인라이어를 찾아 낼 수 있는 방법을 제시한다.

• KEPCO Journal on Electric Power and Energy
• /
• v.8 no.2
• /
• pp.137-141
• /
• 2022

To inspect the power facility faults using artificial intelligence, it need that improve the accuracy of the diagnostic model are required. Data augmentation skill using generative adversarial network (GAN) is one of the best ways to improve deep learning performance. GAN model can create realistic-looking fake images using two competitive learning networks such as discriminator and generator. In this study, we intend to verify the effectiveness of virtual data generation technology by including the fake image of power facility generated through GAN in the deep learning training set. The GAN-based fake image was created for damage of LP insulator, and ResNet based normal and defect classification model was developed to verify the effect. Through this, we analyzed the model accuracy according to the ratio of normal and defective training data.

• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.1
• /
• pp.83-89
• /
• 2023

The Korea Augmentation Satellite System (KASS) system is a Satellite Based Augmentation System (SBAS) under development to provide APV-I SBAS service in the Republic of Korea. The KASS ground segment generates correction and integrity information for GPS measurements of KASS users using the accurate positions of KASS Reference Station (KRS) antenna phase centers. For this reason, the accuracy of KRS reference points through geodetic survey campaigns is one of the important factors for providing the KASS service in compliance with the required navigation performance. In order to obtain accurate positions, two geodetic survey campaigns were performed at several reference points, such as Mark, Center of Mast at Ground Level (CMGL), and Center of Hole in Top Plate (CHTP), of each KRS site using three different survey methods, the Virtual Reference Station (VRS), Flächen Korrektur Parameter (FKP), and raw data post-processing methods. By comparing and analyzing the results, the computed coordinates of the reference points were verified and Antenna Phase Center (APC) positions were calculated using KRS Antenna Reference Point (ARP) data, and the first KASS Site Acceptance Test (SAT#1) was performed successfully using the verified APC coordinates. After the first site survey activities, the KASS operators should maintain the coordinates with the required performance such that the overall KASS navigation performance commitment is guaranteed during the lifetime of 15 years. Therefore, the maintenance plan for the KRS antenna coordinates should be developed before the commissioning of KASS operation planned after 2023. Therefore, this paper presents a geodetic survey method selected for the maintenance activities and provides the rationale for using this method.

• Journal of Internet Computing and Services
• /
• v.16 no.4
• /
• pp.25-37
• /
• 2015

This study has developed a mobile AR contents Builder (MARB) featuring the augmentation of virtual objects, e. g. 2D images, 3D models and videos on user-preferred markers in mobile environment and with connected interaction events. The developed MARB is capable of augmenting multiple virtual objects on markers preferred by users, and selectively supporting many marker-specific interaction events. The MARB is also developed as a mobile App for convenience of use in the mobile environment. This makes users to implement AR contents by a GUI-based authoring procedure on the mobile device. The developed MARB allows App developers and general users to author mobile contents easily and can be applied to various field by those who wish to use diverse mobile AR contents. Moreover, the MARB will provide solutions for the expansion of mobile AR market, by overcoming the difficulties of mobile AR content development.

• Journal of Advanced Navigation Technology
• /
• v.19 no.3
• /
• pp.192-198
• /
• 2015

Since instrument landing system currently operating in most airports is operating in single-pass, it is not possible to accommodate a large number of aircraft. A satellite navigation system GBAS using a GNSS has been developed to solve these limitation when air traffic increases. GBAS is better than the ILS in position accuracy and capable of landing through multiple paths rather than a single path, the aircraft can perform varied landing procedures. In this paper, after we established a virtual ILS procedures at Taean Airfield in which ILS installation is impossible due to environmental requirements and airspace restrictions, flight test was performed by Cessna Skyhawk 172 to compare the virtual ILS procedures and curved approach procedure and the advantage of curved approach was confirmed.

• Journal of Internet Computing and Services
• /
• v.21 no.1
• /
• pp.33-43
• /
• 2020

Retrieving a 3D model from a 3D database and augmenting the retrieved model in the Augmented Reality system simultaneously became an issue in developing the plausible AR environments in a convenient fashion. It is considered that the sketch-based 3D object retrieval is an intuitive way for searching 3D objects based on human-drawn sketches as query. In this paper, we propose a novel deep learning based approach of retrieving a sketch-based 3D object as for an Augmented Reality Model. For this work, we introduce a new method which uses Sketch CNN, Wasserstein CNN and Wasserstein center loss for retrieving a sketch-based 3D object. Especially, Wasserstein center loss is used for learning the center of each object category and reducing the Wasserstein distance between center and features of the same category. The proposed 3D object retrieval and augmentation consist of three major steps as follows. Firstly, Wasserstein CNN extracts 2D images taken from various directions of 3D object using CNN, and extracts features of 3D data by computing the Wasserstein barycenters of features of each image. Secondly, the features of the sketch are extracted using a separate Sketch CNN. Finally, we adopt sketch-based object matching method to localize the natural marker of the images to register a 3D virtual object in AR system. Using the detected marker, the retrieved 3D virtual object is augmented in AR system automatically. By the experiments, we prove that the proposed method is efficiency for retrieving and augmenting objects.