• The Journal of Korean Institute of Information Technology
• /
• v.17 no.6
• /
• pp.9-16
• /
• 2019

Companies that want to improve their manufacturing processes have recently introduced the smart factory, which is particularly noticeable. The ultimate goal is to maximize the area of the smart factory that performs the process of the production facility completely with minimal manual control and to minimize errors of reasoning. This research is a part of a project for unmanned production, management, packaging, and delivery management and the detection of the start point of rebars to perform the automatic calibration of the rollers through the tracking of the automated facilities of unmanned production. It must meet the requirement to accurately track the position from the start point to the end point. In order to improve the tracking performance, it is important to set the accurate start point. However, the probability of tracking errors is high depending on environments such as illumination and dust through the conventional time-based detection method. In this paper, we propose a starting point detection method using the average brightness change of high speed IR camera to reduce the errors according to the environments, As a result, its performance is improved by more than 15%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1312-1319
• /
• 2022

This paper defines an effectiveness index for optical continuous observation of unknown space objects and presents a range of design variables combinations that can satisfy the effectiveness index from a telescope/mount control system perspective using integrated simulation. The overall system-level simulation was implemented and the tracking performance was analyzed by considering design variables such as target position prediction and frame rate, image processing time and measurement error, target trajectory characteristics, and maneuver performance of mount gimbal. As a result of the analysis, it was confirmed that the continuous tracking performance of the optical observation system is dependent on the combination of frame rate and mount maneuver performance. In a situation where an optical observation system is designed or a similar system is implemented using COTS, an appropriate combination of parameters between design variables can be found through effectiveness analysis simulation as in this study.

• Geomechanics and Engineering
• /
• v.28 no.4
• /
• pp.335-346
• /
• 2022

Buckling failure is a typical slope instability mode that should be paid more attention to. It is difficult to provide systematic guidance for the monitoring and management of such slopes due to unclear mechanism. Here we examine buckling failure as the potential instability mode for a slope above a railway tunnel in southwest China. A comprehensive model test system was developed that can be used to conduct buckling failure experiments. The displacement, stress, and strain of the slope were monitored to document the evolution of buckling failure during the experiment. Monitoring data reveal the deformation and stress characteristics of the slope with different slipping mass thicknesses and under different top loads. The test results show that the slipping mass is the main subject of the top load and is the key object of monitoring. Displacement and stress precede buckling failure, so maybe useful predictors of impending failure. However, the response of the stress variation is earlier than displacement variation during the failure process. It is also necessary to monitor the bedrock near the slip face because its stress evolution plays an important role in the early prediction of instability. The position near the slope foot is most prone to buckling failure, so it should be closely monitored.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.6_2
• /
• pp.1119-1125
• /
• 2022

The depletion of resources and waste disposal caused by the continuous development of industry have emphasized the need to reduce consumption and production, recycle and reuse, and the importance of remanufacturing has increased in recent years. The spindle part of the aging planner miller, which is currently being remanufactured, is one of the factors that has the greatest impact on the performance of the machine tool. When designing the spindle part of the spindle shaft, there are considerations such as the configuration size bearing performance of the main shaft, but the diameter of the main shaft, the dangerous speed bearing, and the arrangement that affect the machining accuracy should be basically considered. As such, various studies have been conducted on the design of machine tool spindle spindles, but research on the reverse engineering of existing aging machine tool spindle spindles is poor. Reverse engineering is designing in the direction of improving performance by extracting specifications from already finished products, and first scanning the reverse engineered object through a 3D scanner, 3D modeling is performed based on the collected data, and then the process of deriving improvement plans by reverberating to improve performance by identifying wear and damage conditions is followed. Therefore, in this study, the purpose of this study is to provide data on reverse engineering by deriving improvement plans through optimal design for the bearing position of the aging planar Miller spindle spindle using central composite programming.

• 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.

• Korea Science and Art Forum
• /
• v.24
• /
• pp.375-388
• /
• 2016

Integrated analysis of OST and VST of animation Alladin is carried out in this study. The OST is classified into 4 stages (Introduction, Bridge Passage, Climax, and Ending) and their OST and VST characteristics are found for each step. Especially, high dynamic characteristics of OST elements (sound, tonality, tempo, major range, intensity, and instrumentation) and VST elements (image structure, camera shot, camera movement) are found in the Climax stage. Full Shot is highly used up to 47.9% and this helps to show that the two characters become one in the completion stage of love. This is common factor shown in the previous analysis of OST "Beauty and the Beast". It is also found that specific musical instruments are matched to specific characters in "Beauty and the Beast" and high/low position or up/down movement of the object in the screen are matched to specific musical instruments in 'Alladin'.

• Journal of English Language & Literature
• /
• v.56 no.5
• /
• pp.773-796
• /
• 2010

This essay examines, first, the possibility and limitation of Asian America as a category of identity and its political and cultural implications through various theoretical perspectives. Here, by closely reading David Mura's poem "The Colors of Desire," I will argue that "Asian America" as a category of identity is now on the verge of falling apart and its politics of identity is no longer an effective way of fighting back against racism in the US. It is because Asian America is indeed what might be called a historical block, a product of ad-hoc coalition between different ethnic groups historically situated and constructed. In this sense, it is a kind of phantasmal object that is marked by practical absence. This fabricatedness inherent in Asian America as an identity category signifies that it has no essence that is meant to define the group in a transcendental way. The internal totality and coherence of that identity can thus be achieved only by suppressing differences between various ethnic groups and positing a single 'authentic' Asian American identity and culture. More dangerously, according to Viet Nguyen, such idealization of a single subject position can reinforces ideological rigidity that might threaten the ability of Asian America to represent itself in a unified fashion. Then, he predicts, Asian America will lose its cohesive force and fall apart. Eventually, every group within Asian America will be ethnicized. The only way of escaping from this bleak situation, as Vincent Cheng argues, is to foregroud the fabricatedness and ad-hocness of Asian America and to perform "inauthenticity," because Asian America is nothing but a functional category that is marked by absence of essence or authenticity. If Asian Americans admit that they have no essence and that they are essentially inauthentic, the practice of performing inauthenticity can become what we might call an alternative Asian American culture and identity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2643-2657
• /
• 2023

Scene graphs are structured representations that can clearly convey objects and the relationships between them, but are often heavily biased due to the highly skewed, long-tailed relational labeling in the dataset. Indeed, the visual world itself and its descriptions are biased. Therefore, Unbiased Scene Graph Generation (USGG) prefers to train models to eliminate long-tail effects as much as possible, rather than altering the dataset directly. To this end, we propose Geometric and Semantic Improvement (GSI) for USGG to mitigate this issue. First, to fully exploit the feature information in the images, geometric dimension and semantic dimension enhancement modules are designed. The geometric module is designed from the perspective that the position information between neighboring object pairs will affect each other, which can improve the recall rate of the overall relationship in the dataset. The semantic module further processes the embedded word vector, which can enhance the acquisition of semantic information. Then, to improve the recall rate of the tail data, the Class Balanced Seesaw Loss (CBSLoss) is designed for the tail data. The recall rate of the prediction is improved by penalizing the body or tail relations that are judged incorrectly in the dataset. The experimental findings demonstrate that the GSI method performs better than mainstream models in terms of the mean Recall@K (mR@K) metric in three tasks. The long-tailed imbalance in the Visual Genome 150 (VG150) dataset is addressed better using the GSI method than by most of the existing methods.

• Computers and Concrete
• /
• v.33 no.5
• /
• pp.535-544
• /
• 2024

In the rapidly advancing landscape of computer vision (CV) technology, there is a burgeoning interest in its integration with the construction industry. Camera calibration is the process of deriving intrinsic and extrinsic parameters that affect when the coordinates of the 3D real world are projected onto the 2D plane, where the intrinsic parameters are internal factors of the camera, and extrinsic parameters are external factors such as the position and rotation of the camera. Camera pose estimation or extrinsic calibration, which estimates extrinsic parameters, is essential information for CV application at construction since it can be used for indoor navigation of construction robots and field monitoring by restoring depth information. Traditionally, camera pose estimation methods for cameras relied on target objects such as markers or patterns. However, these methods, which are marker- or pattern-based, are often time-consuming due to the requirement of installing a target object for estimation. As a solution to this challenge, this study introduces a novel framework that facilitates camera pose estimation using standardized materials found commonly in construction sites, such as concrete forms. The proposed framework obtains 3D real-world coordinates by referring to construction materials with certain specifications, extracts the 2D coordinates of the corresponding image plane through keypoint detection, and derives the camera's coordinate through the perspective-n-point (PnP) method which derives the extrinsic parameters by matching 3D and 2D coordinate pairs. This framework presents a substantial advancement as it streamlines the extrinsic calibration process, thereby potentially enhancing the efficiency of CV technology application and data collection at construction sites. This approach holds promise for expediting and optimizing various construction-related tasks by automating and simplifying the calibration procedure.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.77-84
• /
• 2024

In this paper, we propose a method for accurately and rapidly detecting defects in wire harnesses by utilizing computer vision to calculate six crucial measurement values: the length of crimped terminals, the dimensions (width) of terminal ends, and the width of crimped sections (wire and core portions). We employ Harris corner detection to locate object positions from two types of data. Additionally, we generate reference points for extracting measurement values by utilizing features specific to each measurement area and exploiting the contrast in shading between the background and objects, thus reflecting the slope of each sample. Subsequently, we introduce a method using the Euclidean distance and correction coefficients to predict values, allowing for the prediction of measurements regardless of changes in the wire's position. We achieve high accuracy for each measurement type, 99.1%, 98.7%, 92.6%, 92.5%, 99.9%, and 99.7%, achieving outstanding overall average accuracy of 97% across all measurements. This inspection method not only addresses the limitations of conventional visual inspections but also yields excellent results with a small amount of data. Moreover, relying solely on image processing, it is expected to be more cost-effective and applicable with less data compared to deep learning methods.