• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.50 no.9
• /
• pp.417-423
• /
• 2001

This paper proposes a technique for fault detection and classification for both LIF(Low Impedance Fault)s and HIF(High Impedance Fault)s using Adaptive Network-based Fuzzy Inference System(ANFIS). The inputs into ANFIS are current signals only based on Root-Mean-Square(RMS) values of 3-phase currents and zero sequence current. The performance of the proposed technique is tested on a typical 154 kV Korean transmission line system under various fault conditions. Test results show that the ANFIS can detect and classily faults including (LIFs and HIFs) accurately within half a cycle.

• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2234-2236
• /
• 1998

In this paper, we propose a new algorithm based on multi-resolution application of the parameter space to the Hough transform technique. The existing Hough transform technique employs mapping of fixed parameter space in order to extract straight lines from image. One of the difficulties of the existing Hough transform technique lies in the detection of multiple adjacent lines for only one line. Increasing the parameter space from the low level resolution to the high level resolution, our algorithm detects straight line in a stable and efficient fashion. Experimental results are included to verity the performance of proposed algorithm.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2374-2376
• /
• 2001

In this paper we have developed a Power Line Proximity Detecting device for Mobile Crane by using a Derivation Electric-Potential Detection method. A mobile crane worker can be easily exposed to a dangerous electrical shock and the electrocution while they are working at near the high-voltage electrical lines. The derivation electric-potential of the power lines have been simulated in our experiment, Also, microprocessor-based detecting device and transmitter/receiver modules are introduced to show a solution for the dangerous mobile crane working environment. As a result, It has been shown a good functional field test.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.3
• /
• pp.245-250
• /
• 2010

In this paper, an efficient extraction technique of power lines is proposed. Power line extraction technique is used to operate unmanned autonomous vehicles. To achieve the extraction of power lines, an angle space segmentation and grouping method of Hough transform are developed. In simulation results for the proposed algorithm, our algorithm shows a good detection results in experiments for several aerial images which contain different line components.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.9
• /
• pp.63-68
• /
• 2004

The high pressure vessels that are constructed by welding process have many welding lines and most of the leakage defects are occurred on these welding lines. The acoustic emission(AE) technique has adopted to detect the defect location and leakage on welding parts, but the AE signal in leakage are incomplete due to the attenuation, reiteration, instability and limit of defect size. To overcome these troubles, the experiments in this study are conducted to measure the indirect media-propagated AE signal perpendicular to the leakage hole. The AE signals that are acquired from the direct and indirect media are analyzed, and the reliability of the indirect media-propagated AE signal are examined experimentally. By AE signal investigation, this method can be adopted to detect efficiently the leakage in welding parts.

• Journal of Korea Multimedia Society
• /
• v.25 no.5
• /
• pp.695-702
• /
• 2022

In this paper, we propose the method of a table structure recognition in various table types for document processing automation. A table with items surrounded by ruled lines are analyzed by detecting horizontal and vertical lines for recognizing the table structure. In case of a table with items separated by spaces, the table structure are recognized by analyzing the arrangement of row items. After recognizing the table structure, the areas of the table items are input into OCR engine and the character recognition result output to a text file in a structured format such as CSV or JSON. In simulation results, the average accuracy of table item recognition is about 94%.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.6
• /
• pp.337-346
• /
• 2022

This paper addresses the problem of vision-based ear loops ansd attachment inspection in mask production lines. This paper focuses on connections with ear loops and mask filter by an efficient combined approach. The proposed method used a template matching, shape detection and summation of histogram with preprocessing. We had a parameter for detecting defects heuristically. If the shape vertices are lower than the parameters our proposed method will find defective mask automatically. After finding normal masks in mask ear loops attachment status inspection algorithm our proposed method conducts attachment amount inspection. Our experimental results showed that the precision is 1 and the recall is 0.99 in the mask attachment status inspection and attachment amount inspection.

• Journal of The Korean Astronomical Society
• /
• v.37 no.5
• /
• pp.579-581
• /
• 2004

Recently, claims have been made of the detection of 'warm-hot' gas in the intergalactic medium. Kaastra et al. (2003) claimed detection of ${\~} 10^6$ K material in the Coma Cluster but studies by Arnaud et al. (2001), and our analysis of the Chandra observations of Coma (Vikhlinin et al. 2001), find no evidence for a $10^6$ K gas in the cluster. Finoguenov et al. (2003) claimed the detection of $3 {\times} 10^6$ gas slightly off-center from the Coma Cluster. However, our analysis of ROSAT data from this region shows no excess in this region. We propose an alternative explanation which resolves all these conflicting reports. A number of studies (e.g. Robertson et al., 2001) have shown that the local interstellar medium undergoes charge exchange with the solar wind. The resulting recombination spectrum shows lines of O VII and O VIII (Wargelin et al. 2004). Robertson & Cravens (2003) have .shown that as much as $25\%$ of the Galactic polar flux is heliospheric recombination radiation and that this component is highly variable. Sporadic heliospheric emission could account for all the claims of detections of 'warm-hot' gas and explain the conflicts cited above.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.411-420
• /
• 1999

In geology, lineament features have been used to identify geological events, and many of scientists have been developed the algorithm that can be applied with the computer to recognize the lineaments. We choose several edge detection filter, line detection filters and Hough transform to detect an edge, line, and to vectorize the extracted lineament features, respectively. firstly the edge detection filter using a first-order derivative is applied to the original image In this step, rough lineament image is created Secondly, line detection filter is used to refine the previous image for further processing, where the wrong detected lines are, to some extents, excluded by using the variance of the pixel values that is composed of each line Thirdly, the thinning process is carried out to control the thickness of the line. At last, we use the Hough transform to convert the raster image to the vector one. A Landsat image is selected to extract lineament features. The result shows the lineament well regardless of directions. However, the degree of extraction of linear feature depends on the values of parameters and patterns of filters, therefore the development of new filter and the reduction of the number of parameter are required for the further study.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.174-178
• /
• 1999

Recently, the computer vision has been applied to many automation fields. Especially, this paper presents a maritime traffic detection system using computer vision since the high level information can be obtained using obtained area information. The high level informations are obtained such as speed, queueing length, queueing time, ship size, and ship kind. To get ship speed, the two detection lines are set on the predetermined screen position. The speed is obtained the passing time and the predetermined distance between the first and second detection line on the screen. Also, queueing length and time are gotten using screen position of ship. Furthermore, the size and kind of ship are calculated using the ship database and camera calibration data. This developed system contributes to reduce the traffic accidents on the coast. Futhermore, the more information can be extracted using obtained area information.