• The Journal of Korea Robotics Society
• /
• v.14 no.2
• /
• pp.139-149
• /
• 2019

In this paper, we present auto-annotation tool and synthetic dataset using 3D CAD model for deep learning based object detection. To be used as training data for deep learning methods, class, segmentation, bounding-box, contour, and pose annotations of the object are needed. We propose an automated annotation tool and synthetic image generation. Our resulting synthetic dataset reflects occlusion between objects and applicable for both underwater and in-air environments. To verify our synthetic dataset, we use MASK R-CNN as a state-of-the-art method among object detection model using deep learning. For experiment, we make the experimental environment reflecting the actual underwater environment. We show that object detection model trained via our dataset show significantly accurate results and robustness for the underwater environment. Lastly, we verify that our synthetic dataset is suitable for deep learning model for the underwater environments.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.21 no.4
• /
• pp.114-130
• /
• 2022

The purpose of this study was to investigate the possibility of increasing the efficiency of disaster relief rescue operations through collaboration among multiple aerial and ground robots. The robots create 2.5D maps, which are merged into a 2.5D map. The 2.5D map can be handled by a low-specification controller of an aerial robot and is suitable for ground robot navigation. For localization of the aerial robot, a six-degree-of-freedom pose recognition method using VIO was applied. To build a 2.5D map, an image conversion technique was employed. In addition, to merge 2.5D maps, an image similarity calculation technique based on the features on a wall was used. Localization and navigation were performed using a ground robot to evaluate the reliability of the 2.5D map. As a result, it was possible to estimate the location with an average and standard error of less than 0.3 m for the place where the 2.5D map was normally built, and there were only four collisions for the obstacle with the smallest volume. Based on the 2.5D map building and map merging system for the aerial robot used in this study, it is expected that disaster response work efficiency can be improved by combining the advantages of heterogeneous robots.

• Journal of Korea Multimedia Society
• /
• v.10 no.3
• /
• pp.303-315
• /
• 2007

This paper proposes a 3D structure recovery and registration method that uses four or more common points. For each frame of a given video, a partial structure is recovered using tracked points. The 3D coordinates, camera positions and camera directions are computed at once by our improved scaled orthographic factorization method. The partially recovered point sets are parts of a whole model. A registration of point sets makes the complete shape. The recovered subsets are integrated by transforming each coordinate system of the local point subset into a common basis coordinate system. The process of shape recovery and integration is performed uniformly and linearly without any nonlinear iterative process and without loss of accuracy. The execution time for the integration is significantly reduced relative to the conventional ICP method. Due to the fast recovery and registration framework, our shape recovery scheme is applicable to various interactive video applications. The processing time per frame is under 0.01 seconds in most cases and the integration error is under 0.1mm on average.

• Journal of Broadcast Engineering
• /
• v.17 no.4
• /
• pp.611-624
• /
• 2012

'Gesture' is the most intuitive means of communication except the voice. Therefore, there are many researches for method that controls computer using gesture input to replace the keyboard or mouse. In these researches, the method of user detection and main body parts estimation is one of the very important process. in this paper, we propose user objects detection and main body parts estimation method on inaccurate depth information for pose estimation. we present user detection method using 2D and 3D depth information, so this method robust to changes in lighting and noise and 2D signal processing 1D signals, so mainly suitable for real-time and using the previous object information, so more accurate and robust. Also, we present main body parts estimation method using 2D contour information, 3D depth information, and tracking. The result of an experiment, proposed user detection method is more robust than only using 2D information method and exactly detect object on inaccurate depth information. Also, proposed main body parts estimation method overcome the disadvantage that can't detect main body parts in occlusion area only using 2D contour information and sensitive to changes in illumination or environment using color information.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.11
• /
• pp.1131-1135
• /
• 2010

This paper presents a method to capture the posture of the human lower-limbs on the 3D space by using a single camera and a planar mirror. The system estimates the pose of the camera facing the mirror by using four coplanar IR markers attached on the planar mirror. After that, the training space is set up based on the relationship between the mirror and the camera. When a patient steps on the weight board, the system obtains relative position between patients' feet. The markers are attached on the sides of both legs, so that some markers are invisible from the camera due to the self-occlusion. The reflections of the markers on the mirror can partially resolve the above problem with a single camera system. The 3D positions of the markers are estimated by using the geometric information of the camera on the training space. Finally the system estimates and visualizes the posture and motion of the both legs based on the 3D marker positions.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.465-472
• /
• 2022

In this paper, the style synthesis network is trained to generate style-synthesized video through the style synthesis through training Stylegan and the video synthesis network for video synthesis. In order to improve the point that the gaze or expression does not transfer stably, 3D face restoration technology is applied to control important features such as the pose, gaze, and expression of the head using 3D face information. In addition, by training the discriminators for the dynamics, mouth shape, image, and gaze of the Head2head network, it is possible to create a stable style synthesis video that maintains more probabilities and consistency. Using the FaceForensic dataset and the MetFace dataset, it was confirmed that the performance was increased by converting one video into another video while maintaining the consistent movement of the target face, and generating natural data through video synthesis using 3D face information from the source video's face.

• Smart Media Journal
• /
• v.13 no.2
• /
• pp.68-84
• /
• 2024

This paper describes the development of a system and algorithms for high-quality welfare services by recognizing behavior development indicators (activity, sociability, danger) in children aged 0 to 2 years old using action recognition technology. Action recognition targeted 11 behaviors from lying down in 0-year-olds to jumping in 2-year-olds, using data directly obtained from actual videos provided for research purposes by three nurseries in the Gwangju and Jeonnam regions. A dataset of 1,867 actions from 425 clip videos was built for these 11 behaviors, achieving an average recognition accuracy of 97.4%. Additionally, for real-world application, the Edge Video Analyzer (EVA), a behavior analysis device, was developed and implemented with a region-specific random frame selection-based PoseC3D algorithm, capable of recognizing actions in real-time for up to 30 people in four-channel videos. The developed system was installed in three nurseries, tested by ten childcare teachers over a month, and evaluated through surveys, resulting in a perceived accuracy of 91 points and a service satisfaction score of 94 points.

• Geomechanics and Engineering
• /
• v.34 no.3
• /
• pp.251-265
• /
• 2023

In urban construction projects, it is crucial to evaluate the impacts of excavation-induced ground movements in order to protect surrounding structures. These ground movements resulting in damages to the neighboring structures and facilities (i.e., parking basement) are of main concern for the geotechnical engineers. Even more, the danger exists if the nearby structure is an ancient or masonry brick building. The formations of cracks are indicators of structural damage caused by excavation-induced ground disturbances, which pose issues for excavation-related projects. Although the effects of deep excavations on existing brick masonry walls have been thoroughly researched, the impact of twin excavations on a brick masonry wall is rarely described in the literature. This work presents a 3D parametric analysis using an advanced hypoplastic model to investigate the responses of an existing isolated brick masonry wall to twin perpendicular excavations in dry sand. One after the other, twin perpendicular excavations are simulated. This article also looks at how varying sand relative densities (D_r = 30%, 50%, 70%, and 90%) affect the masonry wall. The cracks at the top of the wall were caused by the hogging deformation profile caused by the twin excavations. By raising the relative density from 30% to 90%, excavation-induced footing settlement is greatly minimized. The crack width at the top of the wall reduces as a result of the second excavation in very loose to loose sand (D_r = 30% and 50%). While the crack width on the top of the wall increases owing to the second excavation in medium to very dense sand (D_r = 70% and 90%).

• KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY
• /
• v.29 no.3
• /
• pp.203-209
• /
• 2023

The increasing saturation challenges in storage facilities for Low- and Intermediate-Level Radioactive Waste call for a more efficient storage approach. Consequently, we have developed a square-structured container that features a storage capacity approximately 20% greater than that of conventional drum-type containers. Considering the need to contain various radioactive wastes from nuclear power usage securely until they no longer pose a threat to human health or the environment, this study focuses on evaluating the sealing efficacy of the newly designed rectangular container using finite element analysis. Since radioactive waste containers typically do not experience external forces except under special circumstances, our analysis simulated the impact of an external force, assuming a fall scenario. After fastening the bolts, we examined the vertical stress distribution on the container by applying the calculated external force. The analysis confirms the container's stable seal.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2508-2513
• /
• 2003

This paper presents a nuclear steam generator tube inspection/maintenance robot system. The robot assists in automatic non-destructive testing and the repair of nuclear steam generator tubes welded into a thick tube sheet that caps a hemispherical or quarter-sphere plenum which is a high-radiation area. For easy carriage and installation, the robot system consists of three separable parts: a manipulator, a water-chamber entering and leaving device for the manipulator and a manipulator base pose adjusting device. A software program to control and manage the robotic system has been developed on the NT based OS to increase the usability. The software program provides a robot installation function, a robot calibration function, a managing and arranging function for the eddy-current test, a real time 3-D graphic simulation function which offers remote reality to operators and so on. The image information acquired from the camera attached to the end-effecter is used to calibrate the end-effecter pose error and the time-delayed control algorithm is applied to calculate the optimal PID gain of the position controller. The developed robotic system has been tested in the Ulchin NPP type steam generator mockup in a laboratory.