• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.447-454
• /
• 2024

Construction site monitoring is pivotal for overseeing project progress to ensure that projects are completed as planned, within budget, and in compliance with applicable laws and safety standards. Additionally, it seeks to improve operational efficiency for better project execution. To achieve this, many researchers have utilized computer vision technologies to conduct automatic site monitoring and analyze the operational status of equipment. However, most existing studies estimate real-world 3D information (e.g., object tracking, work status analysis) based only on 2D pixel-based information of images. This approach presents a substantial challenge in the dynamic environments of construction sites, necessitating the manual recalibration of analytical rules and thresholds based on the specific placement and the field of view of cameras. To address these challenges, this study introduces a novel method for 3D visualization and status analysis of construction site objects using 3D reconstruction technology. This method enables the analysis of equipment's operational status by acquiring 3D spatial information of equipment from single-camera images, utilizing the Sam-Track model for object segmentation and the One-2-3-45 model for 3D reconstruction. The framework consists of three main processes: (i) single image-based 3D reconstruction, (ii) 3D visualization, and (iii) work status analysis. Experimental results from a construction site video demonstrated the method's feasibility and satisfactory performance, achieving high accuracy in status analysis for excavators (93.33%) and dump trucks (98.33%). This research provides a more consistent method for analyzing working status, making it suitable for practical field applications and offering new directions for research in vision-based 3D information analysis. Future studies will apply this method to longer videos and diverse construction sites, comparing its performance with existing 2D pixel-based methods.

• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.5
• /
• pp.39-49
• /
• 2017

A Space Launch Vehicle (SLV) for Launching Satellites Consists of Multi-stage Rockets for the Purpose of Efficient Flight and Accomplishes the Launch Mission through Flight Events such as Stage Separation, Engine Start and Stop. In this Process, the SLV is Supposed to Undergo the Processes of the Powered Flight Section in which the Engine Generates Thrust and the Ballistic Flight Section in which there is no Thrust Repeatedly. Because it is Difficult to Express these Flight Characteristics of the SLV as a Single Dynamics Model, much Research on Tracking Algorithms using Multiple Models has been Undertaken. In case of using the Multiple Model Tracking Algorithm, it is Expected to Improve the Tracking Performance of the SLV. However, it is Difficult to Select Proper Dynamics Models to be used and the Calculation Amount Increases due to the use of Multiple Models. In this Paper, we Propose a Method to Track the SLV with Diverse Flight Characteristics Efficiently by only Two Kalman Filters using Constant Acceleration Model and Adaptive Singer Model.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.1
• /
• pp.42-51
• /
• 2007

An AC electrical railroad system has rapidly changing dynamic single-phase load, and at a feeding substation, three-phase electric power is transformed to the paired directional single-phase electric power. There is a great difference in electrical phenomenon between the load of AC electrical railroad system and that of general power system. Electric characteristics of AC electrical railroad's trainload are changed continuously according to the traction, operating characteristic, operating schedule, track slope, etc. Because of the long feeding distance of the dynamic trainload, power quality problems such as voltage drop, voltage imbalance and harmonic distortion my also occur to AC electrical railroad system. These problems affect not only power system stability, but also power quality deterioration in AC electrical railroad system. The dynamic simulation model of AC electrical railroad system presented by PSCAD/EMTDC is modeled in this paper, andthen, it is analyzed voltage drop for AC electrical railroad system both with single-phase distributed STATCOM(Static Synchronous Compensator) installed at SP(Sectioning Post) and without.

• Journal of Cadastre & Land InformatiX
• /
• v.49 no.2
• /
• pp.39-56
• /
• 2019

In this study, we analyzed the effect of the Eungam Loop Line of Seoul Subway Line 6 on the sale price of adjacent row and multi-family houses on the accessibility and structural characteristics of subway stations. This study empirically analyzed a total of 17,938 cases from 2006 to 2017 based on data on the sale price of row and multi-family houses. In summary, the results of this study using the Hedonic Price Model are as follows. First, this study confirms that the Eungam Loop Line characteristics have a positive effect on the sale price as it is adjacent to the subway station. It is noteworthy that the sale price of 100-200m segment has a positive effect, and the sale price of Bulgwang station, which has excellent mobility and connectivity with CBD, YBD and GBD, has a positive effect. Second, this study shows the locational characteristics such as distance to bus stop, distance to mart, and distance to school have influence on the sale price. Third, this study finds the land characteristics such as land area, land shape, land facing, and road width, have significant effects on the sale price. Fourth, this study discovers the sale price is also is also affected by building and floor characteristics such as the type of housing, building area, the number of households, building age, elevator, and floor level.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1321-1330
• /
• 2023

This study attempts to address the problem of 3D pose estimation for multiple human objects through a single image generated during the character development process that can be used in augmented reality. In the existing top-down method, all objects in the image are first detected, and then each is reconstructed independently. The problem is that inconsistent results may occur due to overlap or depth order mismatch between the reconstructed objects. The goal of this study is to solve these problems and develop a single network that provides consistent 3D reconstruction of all humans in a scene. Integrating a human body model based on the SMPL parametric system into a top-down framework became an important choice. Through this, two types of collision loss based on distance field and loss that considers depth order were introduced. The first loss prevents overlap between reconstructed people, and the second loss adjusts the depth ordering of people to render occlusion inference and annotated instance segmentation consistently. This method allows depth information to be provided to the network without explicit 3D annotation of the image. Experimental results show that this study's methodology performs better than existing methods on standard 3D pose benchmarks, and the proposed losses enable more consistent reconstruction from natural images.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.32 no.6
• /
• pp.661-668
• /
• 2012

Wireless sensor network is one of prospective methods for railway monitoring due to the long-term operation and low-maintenance performances. How to supply power to the wireless sensor nodes has drawn much attention recently. In railway monitoring, the idea of converting ambient vibration energy from vibration of railway track induced by passing trains to electric energy has made it a potential way for powering the wireless sensor nodes. In this paper, a bimorph cantilever piezoelectric energy harvester was designed based on a single degree-of-freedom model. Experimental test was also performed to validate the design. The first natural frequency of the bimorph piezoelectric energy harvester was decreased from 117.1 Hz to 65.2 Hz by adding 4 gram tip mass to the free end of the 8.6 gram energy harvester. In addition, the power generation of the piezoelectric energy harvester with 4 gram tip mass at resonant frequency was increased from 0.14 mW to 0.74 mW from $2.06m/s^2$ base excitation compared to stand-alone piezoelectric energy harvester without tip mass.

• Journal of Korean Institute of Industrial Engineers
• /
• v.25 no.3
• /
• pp.342-350
• /
• 1999

Two location algorithm (TLA) considers two location areas (LAs) to track the location of a mobile station (MS). The TLA significantly outperforms the single location algorithm when the call-to-mobility ratio (CMR) is low (i.e., the user moves more frequently than to receive calls). However, because of the paging cost for the users moving back to the previously visited LA, the performance of the TLA degrades when the CMR is high. To reduce those paging cost, we propose the new algorithm called TLA with call information (TLAC). In TLAC, we use the location information of the MS within the setup message when the MS originates a call in the previously visited LA. Through the setup message, the system can know the exact location of the MS without the additional location registration operation, and the paging cost for the arriving calls in the visited LA can be reduced. An analytical model is proposed to compare the TLAC and previous TLA protocol. Our study indicates that the TLAC always guarantees better performance than the TLA. We also observe that the TLAC is much better than the TLA when the CMR is high.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.5
• /
• pp.241-248
• /
• 2000

Until now, all of the port goods are transported manually by container transporter in the port. Recently there are a lot of studies about unmanned vehicle driven automatically. In terms of the vehicle automation, the control of steering and velocity on vehicle systems is very important part in container transporter. In common sense, vehicle systems have lots of nonlinear parameters so we have many difficulties in designing the optimal controller of them. In this paper, we present a design of the TDOF PID controller using a hybrid schematic algorithm to control the steering system optimally. We used the single-track model to pre-test the designed controller before appling to AGV. We also used the ES(evolutionary strategy) and SA(simulated annealing) algorithms to construct the hybrid tuning algorithm for parameters of controller. Finally, we had the computer simulation to verify that our designed controller has better performance than the other one.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.181-186
• /
• 2022

There is a demand for an intermodal automatic transport bogie as a means for efficient logistics transport. Intermodal is characterized by high demand for single-track operation in a specific section in connection with heterogeneous transportation means. In this study, a driving information system that is simple and optimized for the intermodal automatic transportation bogie is implemented to be suitable for the characteristics of the inter-modal automatic transportation bogie, unlike the existing railroad operation system, and applied to a real large-scale demonstration model to ensure in-place stopping and a smooth interface between each system. and operational examples with a simplified system.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.222-234
• /
• 2021

Airborne-pests can be introduced into Korea from overseas areas by wind, which can cause considerable damage to major crops. Meteorological models have been used to estimate the wind trajectories of airborne insects. The objective of this study is to analyze the effect of input settings on the prediction of areas where airborne pests arrive by wind. The wind trajectories were predicted using the HYbrid Single-Particle Lagrangian Integrated Trajectory (HYSPLIT) model. The HYSPLIT model was used to track the wind dispersal path of particles under the assumption that brown plant hopper (Nilaparvata lugens) was introduced into Korea from sites where the pest was reported in China. Meteorological input data including instantaneous and average wind speed were generated using meso-scale numerical weather model outputs for the domain where China, Korea, and Japan were included. In addition, the calculation time intervals were set to 1, 30, and 60 minutes for the wind trajectory calculation during early June in 2019 and 2020. It was found that the use of instantaneous and average wind speed data resulted in a considerably large difference between the arrival areas of airborne pests. In contrast, the spatial distribution of arrival areas had a relatively high degree of similarity when the time intervals were set to be 1 minute. Furthermore, these dispersal patterns predicted using the instantaneous wind speed were similar to the regions where the given pest was observed in Korea. These results suggest that the impact assessment of input settings on wind trajectory prediction would be needed to improve the reliability of an approach to predict regions where airborne-pest could be introduced.