• Proceedings of the KIEE Conference
• /
• 1987.07b
• /
• pp.1367-1370
• /
• 1987

This paper describes a new automatic bi-level image segmentation algorithm which determines local thresholds by applying a locally adaptive edge detection technique to a variable threshold selection method. Computer simulations show that the performance of the proposed algorithm is more robust than those of automatic global thresholding methods.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.25-27
• /
• 2004

Han River water landscape changes between 1966 and 2002 were detected by interpreting IKONOS images, aerial photographs. Digital photogrammetry technique was used in this process. Most of water landscape change are disappearance of sandbars and meandering streams in 1966. It is mainly due to the stream straightening for housing site development.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.33A no.10
• /
• pp.160-167
• /
• 1996

A new pathlength deviation detection technique which is composed of michelson interferometer is described and verified experimentally. The technique uses a sub-threshold biased visible laser diode of 20$\mu$m coherence length as a low-coherent light source. And for zeroth-order fringe(which is the largest among fringes) identification we used a piezoelectric transducer with a large modulation smplitude, which enables without the need of constant velocity scanning, to distinguish reflection surfaces separated by more than 10$\mu$m with a resolution of less than half-wavelength.

• Proceedings of the KIPE Conference
• /
• 1999.07a
• /
• pp.399-402
• /
• 1999

The single sensor technique reconstructing phase currents from the dc-link current without phase current sensors in proposed. When the duration of active vector is too short for the snubber current to reduce, the dc-link current including the snubber current gives large detection error. The solution is presented by analyzing the snubber current and modifying the switching sequences. This scheme is simple, requires only one sampling a period and has good results for detecting the phase currents.

• Journal of the Korean Vacuum Society
• /
• v.1 no.1
• /
• pp.121-125
• /
• 1992

Secondary Ion Mass Spectrometry (SIMS) is widely known as highly sensitive a surface analysis technique. Efforts for quantification have been hindered, however, by the presence of matrix effects. Here we describe a new technique for the quantitative analysis of AlxGa1-xAs. Instead of Al+, Ga+, As+ ions, CsX+ ions (X=Al, Ga, As) have been detected. Intensity of these molecular ions appears to be much less affected by matrix effects. We have successfully accomplished the compositional analysis with standard deviation better than 2 percent.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 1997.11a
• /
• pp.137-146
• /
• 1997

The simplest bit error detection scheme is to append a parity bit to the end of a bit sequence. In this paper an error correction technique with the use of a parity bit is proposed, and the performance of the proposed system is analyzed. The error probability of the proposed system is compared with the output of computer simulation of the proposed system. It is also compared with the error probability of error at BPSK system, and the signal-to-noise ratio gain is showed.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.6
• /
• pp.379-383
• /
• 2015

This paper presents an approach to detect object distance with the use of the recently developed low-cost Kinect sensor. The technique is based on Kinect color depth-image processing and can be used to design various computer-vision applications, such as object recognition, video surveillance, and autonomous path finding. The proposed technique uses keypoint feature detection in the Kinect depth image and advantages of depth pixels to directly obtain the feature distance in the depth images. This highly reduces the computational overhead and obtains the pixel distance in the Kinect captured images.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2005.05a
• /
• pp.511-514
• /
• 2005

Recently, to obtain the reliable data on the state of the structure, various non-destructive techniques are available. The infrared thermography technique is used in detection of cracks, flaws of concrete structures and buildings. In this paper the infrared thermography technique using the difference of surface temperature was studied. Also this paper is case study that the inspection of building's tile using infrared thermal video.

• Proceedings of the KIEE Conference
• /
• 2000.07c
• /
• pp.1891-1893
• /
• 2000

In this paper, we studied the diagnostic technique to analyze the deterioration of cast resin transformer using partial discharge detection for on-site application.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.41-47
• /
• 2024

When there were disparities in performance between models trained in the time and frequency domains, even after conducting an ensemble, we observed that the performance of the ensemble was compromised due to imbalances in the individual model performances. Therefore, this paper proposes a leakage detection technique to enhance the accuracy of pipeline leakage detection through a step-wise learning approach that extracts features from both the time and frequency domains and integrates them. This method involves a two-step learning process. In the Stage 1, independent model training is conducted in the time and frequency domains to effectively extract crucial features from the provided data in each domain. In Stage 2, the pre-trained models were utilized by removing their respective classifiers. Subsequently, the features from both domains were fused, and a new classifier was added for retraining. The proposed transfer learning-based feature fusion technique in this paper performs model training by integrating features extracted from the time and frequency domains. This integration exploits the complementary nature of features from both domains, allowing the model to leverage diverse information. As a result, it achieved a high accuracy of 99.88%, demonstrating outstanding performance in pipeline leakage detection.