• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.2
• /
• pp.1339-1347
• /
• 2015

This study discusses a remote control torch system equipped with a GMAW double wire reel. The welding machine is 30m away from the wire feeder at the industrial site and the feeder is three to five meters away from the torch. Accordingly, the welders cannot control the current and voltage that meets the welding condition during work when they are working at a place that prevents them from seeing the control panel, such as inside a vehicle or tank or at a far work site. They also have no choice but to stop working to change the wire reel when it is burned out completely. Such work suspension resulting from frequent moves to adjust the current and voltage as well as to replace the wire and subsequent cooling causes welding defects. This study produced a remote control torch equipped with a double wire reel by simplifying and streamlining the existing GMAW functions to reduce the troubling issue. The remote control torch equipped with a double wire reel and the existing $CO_2$ /MAG welding torch were applied as a V-groove butt in the vertical position using 6mm rolled steel for a SM50A welding structure. After welding, the condition of welded surface beads underwent a visual inspection and radiographic inspection to analyze the welding quality inside the welded part. This study also evaluated the reduction of welding defects, cost saving, the replacing performance against the existing commercial welders, and the effects on possible compatibility.

• Korean Journal of Remote Sensing
• /
• v.19 no.1
• /
• pp.61-70
• /
• 2003

This paper proposes an autonomous approach to localize the center of fiducial marks included in aerial photographs without precise geometric information and human interactions. For this localization, we present a conceptual model based on two assumptions representing symmetric characteristics of fiducial area and fiducial mark. The model makes it possible to locate exact center of a fiducial mark by checking the symmetric characteristics of pixel value distribution around the mark. The proposed approach is composed of three steps: (a) determining the symmetric center of fiducial area, (b) finding the center of a fiducial mark with unit pixel accuracy, and finally (c) localizing the exact center up to sub-pixel accuracy. The symmetric center of the mark is calculated tv successively applying three geometric filters: simplified ${\nabla}^2$G (Laplacian of Gaussian) filter, symmetry enhancement filter, and high pass filter. By introducing a self-diagnosis function based on the self-similarity measurement, a way of rejecting unreliable cases of center calculation is proposed, as well. The experiments were done with respect to 284 samples of fiducial marks composed of RMK- and RC-style ones extracted from 51 scanned aerial photographs. It was evaluated in the visual inspection that the proposed approach had resulted the erroneous identification with respect to only one mark. Although the proposed approach is based on weak constraints, being free from the exact geometric model of the fiducial marks, experimental results showed that the proposed approach is sufficiently robust and reliable.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.5
• /
• pp.330-335
• /
• 2017

This study applied SONAR(Sound Navigation And Ranging) to the inspection and evaluation of underwater structures. Anactual river bridge was chosen for inspection and evaluation. SONAR and an optical camera were operated together to analyze the underwater image of the bridge. SONAR images were obtained by various methods to remove the environmental variables from the field experiment, and it was confirmed that the reliability of detecting damaged areas on piers was decreased when using SONAR alone. The SONAR equipment and the optical camera can be used simultaneously to overcome the limitations of SONAR in inspecting underwater structures.These results can be used as basic data for the development of similar technologies for underwater structure inspection.

• Journal of Sensor Science and Technology
• /
• v.19 no.3
• /
• pp.169-175
• /
• 2010

Urinalysis is an important clinical test to diagnose urinary diseases, and dipstick method with visual inspection is widely applied in practice. Automated optical devices recently developed have disadvantages of long measurement time, big size and heavy weight, accuracy degradation with time, etc. The present study proposed a new computer scanning technique, in which the test strip and the standard chart were simultaneously scanned to remove any environmental artifacts, followed by automated differentiation with the minimum distance algorithm, leading to significant enhancement of accuracy. Experiments demonstrated an accuracy of 100 % in that all test results were identical with the human visual inspection. The present technique only uses a personal computer with scanner and shortens the test time to a great degree. The results are also stored and accumulated for later use which can be transmitted to remote locations through a network, thus could be easily integrated to any ubiquitous health care systems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.10
• /
• pp.6282-6288
• /
• 2014

$CO_2$ welding is used widely in the field. On the other hand, welding defects occur when welders cannot adjust the current and voltage needed for welding and have to stop working to adjust the current and voltage, causing sudden cooling down of the welding structure inside a vehicle or tank where the control panel is invisible or when work site is far. This study used three types of existing $CO_2$ welders. This also applied SS400 rolled steel for welding structural purposes for remote control torch welding, perform a welding test through v-groove butt welding with a remote control torch and existing $CO_2$ welding torch, conducted visual inspection on the appearance of a welded top bead. In addition, the appearance quality of the welding part was monitored mainly through penetrant testing and a bending test to evaluate the welding defect reduction and the effect on the performance and compatibility by replacing the existing welder.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.959-979
• /
• 2024

Rice pest identification is essential in modern agriculture for the health of rice crops. As global rice consumption rises, yields and quality must be maintained. Various methodologies were employed to identify pests, encompassing sensor-based technologies, deep learning, and remote sensing models. Visual inspection by professionals and farmers remains essential, but integrating technology such as satellites, IoT-based sensors, and drones enhances efficiency and accuracy. A computer vision system processes images to detect pests automatically. It gives real-time data for proactive and targeted pest management. With this motive in mind, this research provides a novel farmland fertility algorithm with a deep learning-based automated rice pest detection and classification (FFADL-ARPDC) technique. The FFADL-ARPDC approach classifies rice pests from rice plant images. Before processing, FFADL-ARPDC removes noise and enhances contrast using bilateral filtering (BF). Additionally, rice crop images are processed using the NASNetLarge deep learning architecture to extract image features. The FFA is used for hyperparameter tweaking to optimise the model performance of the NASNetLarge, which aids in enhancing classification performance. Using an Elman recurrent neural network (ERNN), the model accurately categorises 14 types of pests. The FFADL-ARPDC approach is thoroughly evaluated using a benchmark dataset available in the public repository. With an accuracy of 97.58, the FFADL-ARPDC model exceeds existing pest detection methods.

• Korean Journal of Remote Sensing
• /
• v.26 no.5
• /
• pp.527-536
• /
• 2010

This paper reports a reliable GRD (Ground Resolved Distance) measurement method of using natural targets instead of the method using artificial targets. For this, we developed an edge profile extraction technique suitable for natural targets. We demonstrated the accuracy and stability of this technique firstly by comparing GRD values generated by this technique visually inspected GRD values for artificial targets taken in laboratory environments. We then demonstrated the feasibility of GRD estimation from natural targets by comparing GRD values from natural targets to those from artificial targets using satellite images containing both artificial and natural targets. The GRDs measured from the proposed method were similar to the values from visual inspection and the GRDs measured from the natural targets were similar to the values from artificial targets. These results support our proposed method is able to measure reliable GRD from natural targets.

• Korean Journal of Remote Sensing
• /
• v.35 no.1
• /
• pp.117-136
• /
• 2019

In this study, a hybrid-type of day fog detection algorithm (DFDA) was developed based on the optical and textural characteristics of fog top, using the Himawari-8 /Advanced Himawari Imager data. Supplementary data, such as temperatures of numerical weather prediction model and sea surface temperatures of operational sea surface temperature and sea ice analysis, were used for fog detection. And 10 minutes data from visibility meter from the Korea Meteorological Administration were used for a quantitative verification of the fog detection results. Normalized albedo of fog top was utilized to distinguish between fog and other objects such as clouds, land, and oceans. The normalized local standard deviation of the fog surface and temperature difference between fog top and air temperature were also assessed to separate the fog from low cloud. Initial threshold values (ITVs) for the fog detection elements were selected using hat-shaped threshold values through frequency distribution analysis of fog cases.And the ITVs were optimized through the iteration method in terms of maximization of POD and minimization of FAR. The visual inspection and a quantitative verification using a visibility meter showed that the DFDA successfully detected a wide range of fog. The quantitative verification in both training and verification cases, the average POD (FAR) was 0.75 (0.41) and 0.74 (0.46), respectively. However, sophistication of the threshold values of the detection elements, as well as utilization of other channel data are necessary as the fog detection levels vary for different fog cases(POD: 0.65-0.87, FAR: 0.30-0.53).

• Korean Journal of Remote Sensing
• /
• v.37 no.1
• /
• pp.41-55
• /
• 2021

To detect thunderstorms occurring in Korea, National Meteorological Satellite Center (NMSC) also introduced the rapid-development thunderstorm (RDT) algorithm developed by EUMETSAT. At NMCS, the H-RDT (HR) based on the Himawari-8 satellite and the K-RDT (KR) which combines the GK2A convection initiation output with the RDT were developed. In this study, we optimized the KR (KU) to improve the detection level of thunderstorms occurring in Korea. For this, we used all available data, such as GK2A/AMI, RADAR, lightning, and numerical model data from the recent two years (2019-2020). The machine learning of logistic regression and stepwise variable selection was used to optimize the KU algorithms. For considering the developing stages and duration time of thunderstorms, and data availability of GK2A/AMI, a total of 72 types of detection algorithms were developed. The level of detection of the KR, HR, and KU was evaluated qualitatively and quantitatively using lightning and RADAR data. Visual inspection using the lightning and RADAR data showed that all three algorithms detect thunderstorms that occurred in Korea well. However, the level of detection differs according to the lightning frequency and day/night, and the higher the frequency of lightning, the higher the detection level is. And the level of detection is generally higher at night than day. The quantitative verification of KU using lightning (RADAR) data showed that POD and FAR are 0.70 (0.34) and 0.57 (0.04), respectively. The verification results showed that the detection level of KU is slightly better than that of KR and HR.

• Journal of Digital Convergence
• /
• v.11 no.1
• /
• pp.275-281
• /
• 2013

This space is for the of your study in English. If simple menu item changes or the addition of check items are necessary on GUI menu of existing test equipments for military facilities that are programmed by using RAD tools such as Visual C++, they should go through complex steps, such as numerous conducting steps, coding, flash design modification, recompiling and distribution. It is cumbersome process and waste much time. Also, on implementing them, it was worried about leaking secrets because a number of military security considerations were included. To solve such as the above problem, we proposed commercial RIA technologies and a COTS fault diagnostic knowledge-based system that implemented by the XML data design technique in this research. The proposed approach solves the problem of existing methods, reduced inspection time, and improved performance, usability, and maintainability.