• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.10
• /
• pp.569-574
• /
• 2003

Computer vision system is broadly adapted like as autonomous vehicle system, product line inspection, etc., because it has merits which can deal with environment flexibly. However, for applying it for that industry, it has to clear the problem that recognize position parameter of itself. So that computer vision system stands in need of camera calibration to solve that. Camera calibration consists of the intrinsic parameter which describe electrical and optical characteristics and the extrinsic parameter which express the pose and the position of camera. And these parameters have to be reorganized as the environment changes. In traditional methods, however, camera calibration was achieved at off-line condition so that estimation of parameters is in need again. In this paper, we propose a method to the calibration of camera using line correspondence in image sequence varied environment. This method complements the corresponding errors of the point corresponding method statistically by the extraction of line. The line corresponding method is strong by varying environment. Experimental results show that the error of parameter estimated is within 1% and those is effective.

• Journal of the Society of Naval Architects of Korea
• /
• v.45 no.6
• /
• pp.579-589
• /
• 2008

In the past few years, there are many studies and researches of the underwater vehicles which are carried out its mission using sonar sensors. MSCL(Marine System Control Lab.) at Inha University developed test-bed small ROV, ISRO. ISRO is an open-frame type and has 4 thrusters. ISRO can control 4 motions i.e surge, sway, yaw and heave with sonar sensors. ISRO is developed for inspection of ship hull, marine structure, plant of lake or river and so on. When ROV ISRO inspects something, it is necessary to control the position of ROV ISRO's for the movement and anti-collision with structures in the underwater. In this paper, we deal with the development of a small ROV and verification of the position control system via simulation and experiment using sonar sensors.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.23 no.3
• /
• pp.271-278
• /
• 2015

This paper develops an OBD Diagnostic Program (Program) using Visual Studio (C#), which was used to diagnosis malfunction information from OBD-II system vehicles. We accomplished this using the Program, Diagnostic tests, Board (STN1110), FTDI Basic Cable, Mini USB Cable, OBD Data Cable, and both hybrid and regular vehicles. The Program tests real-time data output, DTC output, sensor value output, engine RPM, waveform data, OBD type check, PID inspection, and whole monitoring. We found vehicles used in this research had 19 PIDs, which was within OBD-II regulations. We also gathered data on control and diagnostic code regulated by OBD-II system, such as, sensor output value, engine RPM, DTC output, each PID analytic value, OBD type, fuel mode, and whole monitoring result value. Using the data collected through the Program appropriately can lead to more effective diagnostic practices and contribute to education.

• Journal of Ocean Engineering and Technology
• /
• v.30 no.5
• /
• pp.374-380
• /
• 2016

The large drift and angle of attack motion of an ROV (Remotely operated vehicle) cannot be modeled using the typical hydrodynamic coefficients of conventional straight running AUVs and specific slender bodies. In this paper, the ROV hull is divided into several simple-shaped components to model the hydrodynamic force and moment. The hydrodynamic force and moment acting on each component are modeled as the components of added mass force and drag using the known values for simple shapes such as a cylinder and flat plate. Since an ROV is operated under the water, the only environmental force considered is the current effect. The target ROV dealt with in this paper has six thrusters, and it is assumed that its maneuvering motion is determined using a thrust allocation algorithm. Tracking simulations are carried out on the ship’s surface near the stern, bow, and midship sections based on the modeling of the hydrodynamic force and current effect.

• Computers and Concrete
• /
• v.23 no.6
• /
• pp.445-457
• /
• 2019

Cracks are an important distress of concrete bridges, and may reduce the life and safety of bridges. However, the traditional manual crack detection means highly depend on the experience of inspectors. Furthermore, it is time-consuming, expensive, and often unsafe when inaccessible position of bridge is to be assessed, such as viaduct pier. To solve this question, the real-time automatic crack detecting system with unmanned aerial vehicle (UAV) become a choice. This paper designs a new automatic detection system based on real-time comprehensive image processing for bridge crack. It has small size, light weight, low power consumption and can be carried on a small UAV for real-time data acquisition and processing. The real-time comprehensive image processing algorithm used in this detection system combines the advantage of connected domain area, shape extremum, morphology and support vector data description (SVDD). The performance and validity of the proposed algorithm and system are verified. Compared with other detection method, the proposed system can effectively detect cracks with high detection accuracy and high speed. The designed system in this paper is suitable for practical engineering applications.

• International Journal of High-Rise Buildings
• /
• v.9 no.4
• /
• pp.351-360
• /
• 2020

Monitoring civil structures periodically is necessary for ensuring the fitness of the structures. Cracks on inner and outer surfaces of the building plays a vital role in indicating the health of the building. Conventionally, human visual inspection techniques were carried up to human reachable altitudes. Monitoring of high rise infrastructures cannot be done using this primitive method. Also, there is a necessity for more accurate prediction of cracks on building surfaces for ensuring the health and safety of the building. The proposed research focused on developing an efficient crack classification model using Transfer Learning enabled EfficientNet (TL-EN) architecture. Though many other pre-trained models were available for crack classification, they rely on more number of training parameters for better accuracy. The TL-EN model attained an accuracy of 0.99 with less number of parameters on large dataset. A bench marked METU dataset with 40000 images were used to test and validate the proposed model. The surfaces of high rise buildings were investigated using vision enabled Unmanned Arial Vehicles (UAV). These UAV is fabricated with TL-EN model schema for capturing and analyzing the real time streaming video of building surfaces.

• Smart Structures and Systems
• /
• v.31 no.5
• /
• pp.501-516
• /
• 2023

Dynamic irregularity and acceleration of bridges subjected to high-speed trains provide crucial information for comprehensive evaluation of the health state of under-track structures. This paper proposes a novel approach for real-time estimation of vertical track dynamic irregularity and bridge acceleration using deep generative adversarial network (GAN) and vibration data from in-service train. The vehicle-body and bogie acceleration responses are correlated with the two target variables by modeling train-bridge interaction (TBI) through least squares generative adversarial network (LSGAN). To realize supervised learning required in the present task, the conventional LSGAN is modified by implementing new loss function and linear activation function. The proposed approach can offer pointwise and accurate estimates of track dynamic irregularity and bridge acceleration, allowing frequent inspection of high-speed railway (HSR) bridges in an economical way. Thanks to its applicability in scenarios of high noise level and critical resonance condition, the proposed approach has a promising prospect in engineering applications.

• Journal of Hydrogen and New Energy
• /
• v.35 no.1
• /
• pp.56-65
• /
• 2024

Fuel cell powered unmanned aerial vehicles (UAV) are globally being developed for various application according to hydrogen roadmap. However, safety standards for hydrogen fuel cell for UAV have not been established. Therefore, in this study, we derive safety data based on risk assessment to develop safety standards for fuel cells for UAV. We use fault tree analysis method which is broadly used in hydrogen facilities as a risk assessment tool. We set hydrogen leaks and fires as top events and derived the basic events. Safety data for the basic events were derived by quoting overseas safety standards related to fuel cells. The safety data will be used for developing fuel cell inspection standard according to Act on Hydrogen Economy Promotion and Hydrogen Safety Management.

• Smart Structures and Systems
• /
• v.33 no.2
• /
• pp.105-118
• /
• 2024

In order to realize tiny bridge crack discovery by UAV-based machine vision, a novel method combining deep learning and tensor voting is proposed. Firstly, the grid images of crack are detected and descripted based on SE-ResNet50 to generate feature points. Then, the probability significance map of crack image is calculated by tensor voting with feature points, which can define the direction and region of crack. Further, the crack detection anchor box is formed by non-maximum suppression from the probability significance map, which can improve the robustness of tiny crack detection. Finally, a case study is carried out to demonstrate the effectiveness of the proposed method in the Xiangjiang-River bridge inspection. Compared with the original tensor voting algorithm, the proposed method has higher accuracy in the situation of only 1-2 pixels width crack and the existence of edge blur, crack discontinuity, which is suitable for UAV-based bridge crack discovery.

• Journal of Aerospace System Engineering
• /
• v.15 no.5
• /
• pp.81-88
• /
• 2021

In general, a non-explosive nylon wire cutting-based holding and release mechanism has been used to store and deploy deployable solar panels of CubeSat. However, with this method, accessing the solar panel's access port for charging the cube satellite's battery and electrical inspection and testing of the PCB and payloads while the solar panel is in storage is difficult. Additionally, the mechanism must have a reliable release function in an in-orbit environment, and reusability for stow and deploy of the solar panel, which is a hassle for the operator and difficult to maintain a consistent nylon wire fastening process. In this study, we proposed a pin-puller-based solar panel holding and release mechanism that can easily deploy a solar panel without cutting nylon wires by separating constraining pins. The proposed mechanism's release function and performance were verified through a solar panel deployment test and a maximum separation load measurement test. Through this, we also verified the design feasibility and effectiveness of the pin-puller-based separation device.