• The Journal of the Convergence on Culture Technology
• /
• v.5 no.1
• /
• pp.77-82
• /
• 2019

AI is applied increasingly to overall industries such as living, medical, financial service, autonomous car, etc. thanks to rapid technology development. AI-leading countries are strengthening their competency to secure competitiveness since AI is positioned as the core technology in $4^{th}$ Industrial Revolution. Although Korea has the competitive IT infra and human resources, it lags behind traditional AI-leaders like United States, Canada, Japan and, even China which devotes all its might to develop intelligent technology-intentive industry. AI is the critical technology influencing on the national industry in the near future according to advancement of intelligent information society so that concentration of capability is required with national interest. Also, joint development with global AI-leading companies as well as development of own technology are crucial to prevent technology subordination. Additionally, regulatory reform and preparation of related law are very urgent.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.5
• /
• pp.205-212
• /
• 2019

Scene graph is a kind of knowledge graph that represents both objects and their relationships found in a image. This paper proposes a 3D scene graph generation model for three-dimensional indoor environments. An 3D scene graph includes not only object types, their positions and attributes, but also three-dimensional spatial relationships between them, An 3D scene graph can be viewed as a prior knowledge base describing the given environment within that the agent will be deployed later. Therefore, 3D scene graphs can be used in many useful applications, such as visual question answering (VQA) and service robots. This proposed 3D scene graph generation model consists of four sub-networks: object detection network (ObjNet), attribute prediction network (AttNet), transfer network (TransNet), relationship prediction network (RelNet). Conducting several experiments with 3D simulated indoor environments provided by AI2-THOR, we confirmed that the proposed model shows high performance.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.2
• /
• pp.345-353
• /
• 2019

The Video See-through HMD(VSHMD) captures real-world view through a camera set mounted in front of the HMD. The VSHMD outputs this visual information in real time through the display in the HMD, which technique can be used as mixed reality, augmented reality, and virtual reality device. Recently, there is growing interest in VSHMD due to the rapid development of camera and display technology. However, VSHMD is still not free from many technical huddles and human factor issues. This paper summarizes the VSHMD related researches so far, presents the major issues to be solved in advance, and suggests design considerations that should be beneficial to VSHMD development, focused on the human factors, that presents solutions to effectively overcome the limitations of VSHMD functionalities in current.

• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.5
• /
• pp.105-113
• /
• 2019

Korean military uses 'Tactical information communication network' to exchange information between units. In this study, we developed a media processing board for multi-party voice and video telephony based on open source software. On the other hand, in order to apply open source software for weapon systems and parts that are mounted on weapon systems, appropriate review is required according to the weapon system software development and management manual of the Defense Acquisition Program Administration (DAPA). In this study, the analysis of the requirement items was performed and the appropriate countermeasures were proposed for the open software applied to the media processing board with respect to 'the guidelines for the application of weapon systems to open source software', an appendix to the DAPA's manual.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.2
• /
• pp.35-41
• /
• 2021

In this study, improved path tracking control algorithm based on pure pursuit algorithm is newly proposed by using improved lane detection algorithm through real time post-processing with interpolation methodology. Since the original pure pursuit works well only at speeds below 20 km/h, the look-ahead distance is implemented as a sigmoid function to work well at an average speed of 45 km/h to improve tracking performance. In addition, a smoothing filter was added to reduce the steering angle vibration of the original algorithm, and the stability of the steering angle was improved. The post-processing algorithm presented has implemented more robust lane recognition system using real-time pre/post processing method with deep learning and estimated interpolation. Real time processing is more cost-effective than the method using lots of computing resources and building abundant datasets for improving the performance of deep learning networks. Therefore, this paper also presents improved lane detection performance by using the final results with naive computer vision codes and pre/post processing. Firstly, the pre-processing was newly designed for real-time processing and robust recognition performance of augmentation. Secondly, the post-processing was designed to detect lanes by receiving the segmentation results based on the estimated interpolation in consideration of the properties of the continuous lanes. Consequently, experimental results by utilizing driving guidance line information from processing parts show that the improved lane detection algorithm is effective to minimize the lateral offset error in the diverse maneuvering roads.

• Journal of Platform Technology
• /
• v.8 no.1
• /
• pp.24-32
• /
• 2020

This paper designed and manufactured a chip mounter based on 3D printer technology that can be used for educational research or sample production to disseminate chip mounter, a core technology of SMT line. A stepper motor with open loop control is used for low cost drive design. The shortcomings of the motor's vibration and disassembly caused by the use of the step motor were compensated by the Micro-Step control method. In the chip mounter experiment, the gerber file was generated on the small chip mounter, printed at the actual size, and the solder cream was printed on the HASL-treated PCB in the same manner as the sample board fabrication. As a result of the experiment, unlike the 2012 micro components, parts such as SOIC and TQFP that require correction are twice as long as the component mounting time, but it can be confirmed that they are mounted relatively accurately. In addition, as a result of repeatedly measuring the error of the initial position 10 times, it was confirmed that a relatively small error of about 0.110mm occurs.

• The Journal of the Korea Contents Association
• /
• v.21 no.5
• /
• pp.996-1003
• /
• 2021

The purpose of this study is to evaluate the reliability of repeated measurements of several dental scanners. Blue-lighted scanners, white-light scanners and optical-type scanners are used in the study of repeatability in this study. The measurement results were calculated as root mean square (RMS) and the significance level was confirmed by applying the 1-way ANOVA statistical technique (𝛼=.05). According to the statistical analysis, the scanner with the largest RMS value was Z-opt group (38.2 ㎛. Next, D-white was 35.2 ㎛ and the group with the lowest RMS value was I-blue (34.1 ㎛). The comparison of RMS means between each group was not significant (p>.05). From this result, the blue light had the lowest error in repeatability of dental scanners, but no statistical significance. The conclusion of this study is that the study results are clinically acceptable.

• Journal of Advanced Navigation Technology
• /
• v.26 no.4
• /
• pp.235-243
• /
• 2022

In this paper, in the case of an inertial navigation system, the posture estimation error in the initial alignment due to vertical deflection is analyzed. Posture estimation error due to DOV was theoretically analyzed based on the speed and posture error of INS. Simulations were performed to verify the theoretical grinding, and the results were in good agreement. For example, in the case of η=20", an alignment error of ϕ_N=0.00287°, ϕ_U=0.00196° occurred, and in the case of 𝜉=20", an error of ϕ_E= -0.00286° occurred. Through this, it was confirmed that the vertical posture error caused by the DOV occurred as a coupling characteristic of the INS posture error. It has been shown that an additional posture error may occur due to the DOV, which was not considered in the existing INS alignment, which means that correction for the DOV must be considered when applying high-precision INS.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.779-785
• /
• 2022

Study analyzes whether the 3D CAD class using the flipped learning-based PBL is effective in acquiring professional knowledge and nurturing talent. A Flipped Learning-based PBL class was implemented for 3rd grade students of Robot and Automation Engineering Major, Dong-Eui University, and a survey was conducted on satisfaction and effectiveness. The students seemed to be generally satisfied with the class, and the flipped learning-based PBL appeared to be effective in improving the competency required by companies. In particular, it is hoped that it will contribute to the use of video education in practical subjects in the future by proving that practical classes can be operated effectively even in non-face-to-face learning. Moreover, this study is an important indicator for future research and will be used as a quantitative indicator for class improvement.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.738-747
• /
• 2021

Today, with the improvement of deep learning technology, computer vision areas such as image classification, object detection, object segmentation, and object tracking have shown remarkable improvements. Various applications such as intelligent surveillance, robots, Internet of Things, and autonomous vehicles in combination with deep learning technology are being applied to actual industries. Accordingly, the requirement of an efficient compression method for video data is necessary for machine consumption as well as for human consumption. In this paper, we propose an object-based compression of thermal infrared images for machine vision. The input image is divided into object and background parts based on the object detection results to achieve efficient image compression and high neural network performance. The separated images are encoded in different compression ratios. The experimental result shows that the proposed method has superior compression efficiency with a maximum BD-rate value of -19.83% to the whole image compression done with VVC.