• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.221-223
• /
• 2016

Currently in the automobile market, models with many convenient functions combined with IT have been released. This change has a strength that there could be many convenient and useful functions related to driving while flaws of vehicles caused by malfunctions of these electronic equipments could trigger serious incidents. Among them, the sudden unintended acceleration considered as the most serious is a serious flaw that could threaten driver's life. However, the causes for sudden acceleration incidents have not been clearly investigated with no coping measures. As manufacturers shift the responsibility to drivers' carelessness, drivers' burden is continuously increasing. Thus, this paper designed the system to cope with sudden acceleration incidents by changing conditions of controlling parts like accelerator and brake, and internal image of the driver's seat into data through the integrated module.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.2
• /
• pp.140-152
• /
• 2021

During the shift from gasoline vehicles to electric ones, auto parts manufacturing companies have realized the importance of improvement in the manufacturing process that does not require any layout changes nor extra investments, while maintaining their current production rate. Due to these reasons, for the auto part manufacturing company, I-company, this study has developed the simulation model of the PUSH system to conduct a process analysis in terms of production rate, WIP level, and logistics work's utilization rate. In addition, this study compares the PUSH system with other three manufacturing systems -KANBAN, DBR, and CONWIP- to compare the performance of these production systems, while satisfying the company's target production rate. With respect to lead-time, the simulation results show that the improvement of 77.90% for the KANBAN system, 40.39% for the CONWIP system, and 69.81% for the DBR system compared to the PUSH system. In addition, with respect to WIP level, the experimental results demonstrate that the improvement of 77.91% for the KANBAN system, 40.41% for the CONWIP system, and 69.82% for the DBR system compared to the PUSH system. Since the KANBAN system has the largest impacts on the reduction of the lead-time and WIP level compared to other production systems, this study recommends the KANBAN system as the proper manufacturing system of the target company. This study also shows that the proper size of moving units is four and the priority allocation of bottleneck process methods improves the target company's WIP and lead-time. Based on the results of this study, the adoption of the KANBAN system will significantly improve the production process of the target company in terms of lead-time and WIP level.

• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.93-101
• /
• 2023

In this paper, we propose a method of creating a 3D bounding box for an object using a vanishing point to increase the accuracy of object recognition in an image when recognizing an traffic object using a video camera. Recently, when vehicles captured by a traffic video camera is to be detected using artificial intelligence, this 3D bounding box generation algorithm is applied. The vertical vanishing point (VP1) and horizontal vanishing point (VP2) are derived by analyzing the camera installation angle and the direction of the image captured by the camera, and based on this, the moving object in the video subject to analysis is specified. If this algorithm is applied, it is easy to detect object information such as the location, type, and size of the detected object, and when applied to a moving type such as a car, it is tracked to determine the location, coordinates, movement speed, and direction of each object by tracking it. Able to know. As a result of application to actual roads, tracking improved by 10%, in particular, the recognition rate and tracking of shaded areas (extremely small vehicle parts hidden by large cars) improved by 100%, and traffic data analysis accuracy was improved.

• Transactions of Materials Processing
• /
• v.31 no.1
• /
• pp.17-22
• /
• 2022

Hot stamping is widely used to manufacture structural parts to satisfy requirements of eco-friendly vehicles. Recently, hot forming technology using uncoated steel sheet is being studied to reduce cost and solve patent problems. In particular, research is focused on process technology capable of suppressing the generation of an oxide layer. To evaluate the oxide layer in the hot stamping process, Gleeble testing machine can be used to evaluate the oxide layer by controlling the temperature history and the atmosphere condition. At this time, since cooling by gas injection is impossible to protect the oxide layer on the surface of a specimen, research on a method for securing a quenching speed through natural cooling is required. This paper proposes a specimen shape design method to secure a target quenching speed through natural cooling when evaluating the oxide layer of an un-coated boron steel sheet by Gleeble test. For the evaluation of the oxide layer of the un-coated steel sheet through the Gleeble test, dog-bone and rectangular type specimens were used. In consideration of the hot stamping process, the temperature control conditions for the Gleeble test were set and the quenching speed according to the specimen shape design was measured. Finally, the quenching speed sensitivity according to shape parameter was analyzed through regression analysis. A quenching speed prediction equation was then constructed according to the shape of the specimen. The constructed quenching speed prediction equation can be used as a specimen design guideline to secure a target quenching speed when evaluating the oxide layer of an un-coated boron steel sheet by the Gleeble test.

• Journal of the Korean Institute of Rural Architecture
• /
• v.23 no.4
• /
• pp.1-12
• /
• 2021

Recently, the use of unmanned aerial vehicles (UAVs) is increasing in the field of land information acquisition and terrain exploration through high-altitude aerial photography. High-altitude aerial photography is suitable for large-scale geographic information collection, but has the disadvantage that it is difficult to accurately collect small-scale geographic information. Therefore, this study used low-altitude UAV to monitor changes in small rural spaces around rural resources, and the results are as follows. First, the low-altitude aerial imagery had a very high spatial resolution, so it was effective in reading and analyzing topographic features. Second, an area with a large number of aerial images and a complex topography had a large amount of point clouds to be extracted, and the number of point clouds affects the three-dimensional quality of rural space. Third, 3D mapping technology using point cloud is effective for monitoring rural space and rural resources because it enables observation and comparison of parts that cannot be read from general aerial images. In this study, the possibility of rural space analysis of low-altitude UAV was verified through aerial photography and analysis, and the effect of 3D mapping on rural space monitoring was visually analyzed. If data acquired by low-altitude UAV are used in various forms such as GIS analysis and topographic map production it is expected to be used as basic data for rural planning to maintain and preserve the rural environment.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.125-134
• /
• 2022

This paper implements an AR manual for a vehicle that can be used even in the vehicle interior space where it is difficult to apply the augmentation method of AR content, which is mainly used, and applies a deep learning model to improve the augmentation matching between real space and virtual objects. Through deep learning, the logo of the steering wheel is recognized regardless of the position, angle, and inclination, and 3D interior space coordinates are generated based on this, and the virtual button is precisely augmented on the actual vehicle parts. Based on the same learning model, the function to recognize the main warning light symbols of the vehicle is also implemented to increase the functionality and usability as an AR manual for vehicles.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.25 no.6
• /
• pp.74-86
• /
• 2021

The composite lattice structure is a structure that supports the required load with the minimum weight and thickness. Composite lattice structure is manufactured by the filament winding process using impregnating high-strength carbon fiber with an epoxy resin. Filament winding process can laminate and manufacture only structurally necessary parts, composite lattice structure can be applied to aircraft fuselages, satellite and launch vehicles, and guided weapons to maximize weight reduction. In this paper, the development and evaluation of the composite lattice structure corresponding to the entire process from design, analysis, fabrication, and evaluation of large-scale cylindrical and conical composites lattice structure were performed. To be applicable to actual projectiles and guided weapons, we developed a cylindrical lattice structure with a diameter of 2,600 mm and a length of 2,000 mm, and a conical lattice structure with an upper diameter of 1,300 mm, a lower diameter of 2,500 mm, and a length of 900 mm. The performance of the developed composite lattice structure was evaluated through a load test.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.351-363
• /
• 2023

Visual structural inspections are an inseparable part of post-earthquake damage assessments. With unmanned aerial vehicles (UAVs) establishing a new frontier in visual inspections, there are major computational challenges in processing the collected massive amounts of high-resolution visual data. We propose twin deep learning models that can provide accurate high-resolution structural components and damage segmentation masks efficiently. The traditional approach to cope with high memory computational demands is to either uniformly downsample the raw images at the price of losing fine local details or cropping smaller parts of the images leading to a loss of global contextual information. Therefore, our twin models comprising Trainable Resizing for high-resolution Segmentation Network (TRS-Net) and DmgFormer approaches the global and local semantics from different perspectives. TRS-Net is a compound, high-resolution segmentation architecture equipped with learnable downsampler and upsampler modules to minimize information loss for optimal performance and efficiency. DmgFormer utilizes a transformer backbone and a convolutional decoder head with skip connections on a grid of crops aiming for high precision learning without downsizing. An augmented inference technique is used to boost performance further and reduce the possible loss of context due to grid cropping. Comprehensive experiments have been performed on the 3D physics-based graphics models (PBGMs) synthetic environments in the QuakeCity dataset. The proposed framework is evaluated using several metrics on three segmentation tasks: component type, component damage state, and global damage (crack, rebar, spalling). The models were developed as part of the 2^nd International Competition for Structural Health Monitoring.

• Nuclear Engineering and Technology
• /
• v.55 no.1
• /
• pp.364-372
• /
• 2023

The space reactor is the primary energy supply for future space vehicles and space stations. The radiator is one of the essential parts of a space reactor. Therefore, the research on radiators can improve the heat dissipation power, reduce the quality of radiators, and make the space reactor smaller. Based on MOOSE multi-physics numerical calculation platform, a simulation program for the combination of heat pipe and fin at the end of heat pipe radiator is developed. It is verified that the calculation result of this program is accurate and the calculation speed is fast. Analyze the heat transfer characteristics of the combination with heat pipe and fin, and obtain its internal temperature field. Based on the calculation results, the influence of structural parameters on the heat dissipation power is analyzed. The results show that when the fin width is 0.25 m, fin thickness is 0.002 m, condensing section length is 0.5425 m and heat pipe radius is 0.014 m, the power-mass ratio is the highest. When the temperature is 700K-900K, the heat dissipation power increases 41.12% for every 100K increase in the operating temperature. Smaller fin width and thinner fin thickness can improve the power-mass ratio and reduce the radiator quality.