• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2008.11a
• /
• pp.243-244
• /
• 2008

• Journal of information and communication convergence engineering
• /
• v.19 no.2
• /
• pp.93-101
• /
• 2021

Cardiac arrhythmias are common heart diseases and generally cause sudden cardiac death. Electrocardiogram (ECG) is an effective tool that can reveal the electrical activity of the heart and diagnose cardiac arrhythmias. We propose detection of P waves based on QRST cancellation zero-one substitution. After preprocessing, the QRST segment is determined by detecting the Q wave start point and T wave end point separately. The Q wave start point is detected by digital analyses of the QRS complex width, and the T wave end point is detected by computation of an indicator related to the area covered by the T wave curve. Then, we determine whether the sampled value of the signal is in the interval of the QRST segment and substitute zero or one for the value to cancel the QRST segment. Finally, the maximum amplitude is selected as the peak of the P wave in each RR interval of the residual signal. The average detection rate for the QT database was 97.67%.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.415-418
• /
• 1996

Etching Process, one of the most important process in semiconductor fabrication, has input control part of which components are pressure, gas flow, RF power and etc., and plasma gas which is complex and not exactly understood is used to etch wafer in etching chamber. So this process has not real-time feedback controller based on input-output relation, then it uses EPD(End Point Detection) signal to determine when to start or when to stop etching. Various type EPD controller control etching process using EPD signal obtained from optical intensity of etching chamber. In development EPD controller we concentrate on compensation of this signal intensity and setting the relative signal magnitude at first of etching. We compensate signal intensity using neural network learning method and set the relative signal magnitude using fuzzy inference method. Potential of this method which improves EPD system capability is proved by experiences.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.1
• /
• pp.1-11
• /
• 2023

Deep-learning-based image segmentation is one of the most widely employed lane detection approaches, and it requires a post-process for extracting the key points on the lanes. A general approach for key-point extraction is using a fixed threshold defined by a user. However, finding the best threshold is a manual process requiring much effort, and the best one can differ depending on the target data set (or an image). We propose a novel key-point extraction algorithm that automatically adapts to the target image without any manual threshold setting. In our adaptive key-point extraction algorithm, we propose a line-level normalization method to distinguish the lane region from the background clearly. Then, we extract a representative key point for each lane at a line (row of an image) using a kernel density estimation. To check the benefits of our approach, we applied our method to two lane-detection data sets, including TuSimple and CULane. As a result, our method achieved up to 1.80%p and 17.27% better results than using a fixed threshold in the perspectives of accuracy and distance error between the ground truth key-point and the predicted point.

• The Journal of the Korea Contents Association
• /
• v.13 no.8
• /
• pp.1-10
• /
• 2013

This paper proposes a method to detect vanishing points of an indoor scene using line segment classification. Two-stage vanishing points detection is carried out to detect vanishing point in indoor scene efficiently. In the first stage, the method examines whether the image composition is a one-point perspective projection or a two-point one. If it is a two-point perspective projection, a horizontal line through the detected vanishing point is found for line segment classification. In the second stage, the method detects two vanishing points exactly using line segment classification. The method is evaluated by synthetic images and an image DB. In the synthetic image which some noise is added in, vanishing point detection error is under 16 pixels until the percent of the noise to the image becomes 60%. Vanishing points detection ratio by A.Quattoni and A.Torralba's image DB is over 87%.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.54-60
• /
• 2021

AR (Augmented Reality) is a technology that provides virtual content to the real world and provides additional information to objects in real-time through 3D content. In the past, a high-performance device was required to experience AR, but it was possible to implement AR more easily by improving mobile performance and mounting various sensors such as ToF (Time-of-Flight). Also, the importance of mobile augmented reality is growing with the commercialization of high-speed wireless Internet such as 5G. Thus, this paper proposes a system that can provide AR services via GNN (Graph Neural Network) using cameras and sensors on mobile devices. ToF of mobile devices is used to capture depth maps. A 3D point cloud was created using RGB images to distinguish specific colors of objects. Point clouds created with RGB images and Depth Map perform downsampling for smooth communication between mobile and server. Point clouds sent to the server are used for 3D object detection. The detection process determines the class of objects and uses one point in the 3D bounding box as an anchor point. AR contents are provided through app and web through class and anchor of the detected object.

• Journal of the Korea Society of Computer and Information
• /
• v.3 no.2
• /
• pp.85-97
• /
• 1998

The existing edge detection methods can not represent the real edge of object at fitting point or detect the edge which has unsufficient connecting trait. Especially, the two-fold thick edge detected by these methods cannot coincide real boundary of subject and it's location. To overcome these problems, we introduce the Genetic Algorithm(GA) in edge detection. The energy function is the value of fixel's satisfaction degree to edge condition. And it consists of the fitness value to image formation type, fitness value to connecting trait to it's neighboring edge and evalulation function which can represents the edge at fitting point as one fixel. This method is superior to remove the noise in edge detection than the existing methods. And it also detects the clear and exact edge because it can find the one fixel which is located at fitting point and has strong connecting trait.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.1
• /
• pp.49-55
• /
• 2015

In this paper, we propose a fast interest point detection method using SURF algorithm. Since the SURF algorithm needs a great computations to detect the interest points and obtain the corresponding descriptors, it is not suitable for real-time based applications. In order to overcome this problem, the interest point detection step is parallelized by OpenMP and SIMD based on analysis of the scale space representation process and localization one in the step. The simulation results demonstrate that processing speed is enhanced about 55% by applying the proposed method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.9C
• /
• pp.860-867
• /
• 2003

In this paper, an efficient core point detection method using orientation pattern labeling is proposed in fingerprint image. The core point, which is one of the singular points in fingerprint image, is used as the reference point in the most fingerprint recognizing system. Therefore, the detection of the core point is the most essential step of the fingerprint recognizing system, it can affect in the whole system performance. The proposed method could detect the position of the core point by applying the labeling method for the directional pattern which is come from the distribution of the ridges in fingerprint image and applying detailed algorithms for the decision of the core point's position. The simulation result of proposed method is better than the result of Poincare index method and the sine map method in executing time and detecting rate. Especially, the Poincare index method can't detect the core point in the detection of the arch type and the sine map method takes too much times for executing. But the proposed method can overcome these problems.

• The Journal of Korea Robotics Society
• /
• v.10 no.1
• /
• pp.33-41
• /
• 2015

Recent developments in robotics and intelligent vehicle area, bring interests of people in an autonomous driving ability and advanced driving assistance system. Especially fully automatic parking ability is one of the key issues of intelligent vehicles, and accurate parked vehicles detection is essential for this issue. In previous researches, many types of sensors are used for detecting vehicles, 2D LiDAR is popular since it offers accurate range information without preprocessing. The L shape feature is most popular 2D feature for vehicle detection, however it has an ambiguity on different objects such as building, bushes and this occurs misdetection problem. Therefore we propose the accurate vehicle detection method by using a 3D complete vehicle model in 3D point clouds acquired from front inclined 2D LiDAR. The proposed method is decomposed into two steps: vehicle candidate extraction, vehicle detection. By combination of L shape feature and point clouds segmentation, we extract the objects which are highly related to vehicles and apply 3D model to detect vehicles accurately. The method guarantees high detection performance and gives plentiful information for autonomous parking. To evaluate the method, we use various parking situation in complex urban scene data. Experimental results shows the qualitative and quantitative performance efficiently.