• Journal of Biomedical Engineering Research
• /
• v.22 no.6
• /
• pp.503-510
• /
• 2001

In this paper. we describe a 32-channel bioimpedance measurement system It consists of 32 independent constant current sources of 50 kHz sinusoid. The amplitude of each current source can be adjusted using a 12-bit MDAC. After we applied a pattern of injection currents through 32 current injection electrodes. we measured induced boundary voltages using a variable-gain narrow-band instrumentation amplifier. a Phase-sensitive demodulator. and a 12-bit ADC. The system is interfaced to a PC for the control and data acquisition. We used the system to detect anomalies with different resistivity values in a saline Phantom with 290mm diameter The accuracy of the developed system was estimated as 2.42% and we found that anomalies larger than 8mm in diameter can be detected. We Plan to improve the accuracy by using a digital oscillator improved current sources by feedback control, Phase-sensitive A/D conversion. etc. to detect anomalies smaller than 1mm in diameter.

• Journal of KIISE
• /
• v.42 no.5
• /
• pp.642-651
• /
• 2015

A vanishing point is a point where parallel lines converge, and they become evident when a camera's lenses are used to project 3D space onto a 2D image plane. Vanishing point detection is the use of the information contained within an image to detect the vanishing point, and can be utilized to infer the relative distance between certain points in the image or for understanding the geometry of a 3D scene. Since parallel lines generally exist for the artificial structures within images, line-detection-based vanishing point-detection techniques aim to find the point where the parallel lines of artificial structures converge. To detect parallel lines in an image, we detect edge pixels through edge detection and then find the lines by using the Hough transform. However, the various textures and noise in an image can hamper the line-detection process so that not all of the lines converging toward the vanishing point are obvious. To overcome this difficulty, it is necessary to assign a different weight to each line according to the degree of possibility that the line passes through the vanishing point. While previous research studies assigned equal weight or adopted a simple weighting calculation, in this paper, we are proposing a new method of assigning weights to lines after noticing that the lines that pass through vanishing points typically belong to artificial structures. Experimental results show that our proposed method reduces the vanishing point-estimation error rate by 65% when compared to existing methods.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.359-365
• /
• 2021

GEO-KOMPSAT-2A (GK2A) AMI (Advanced Meteorological Imager) Best Detector Select (BDS) map is pre-determined and uploaded before the satellite launch. After the launch, there is some possibility of a detector performance change driven by an abrupt temperature variation and thus the status of BDS map needs to be evaluated and updated if necessary. To investigate performance of entire elements of the detectors, AMI BDS analyses were conducted based on a technical note provided from the AMI vendor (L3HARRIS). The concept of the BDS analysis is to investigate the stability of signals from detectors while they are staring at targets (deep space and internal calibration target). For this purpose, Long Time Series (LTS) and Output Voltage vs. Bias Voltage (V-V) methods are used. The LTS for 30 secs and the V-V for two secs are spanned respectively for looking at the targets to compute noise components of detectors. To get the necessary data sets, these activities were conducted during the In-Orbit Test (IOT) period since a normal operation of AMI is stopped and special mission plans are commanded. With collected data sets during the GK2A IOT, AMI BDS map was intensively examined. It was found that about 1% of entire detector elements, which were evaluated at the ground test, showed characteristic changes and those degraded elements are replaced by alternative best ones. The stripping effects on AMI raw images due to the BDS problem were clearly removed when the new BDS map was applied.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.43-49
• /
• 2019

The wired and wireless Internet is a useful window to easily acquire various types of media data. On the other hand, the public can easily get the media data including the object to which the personal information is exposed, which is a social problem. In this paper, we propose a method to robustly detect a target object that has exposed personal information using a learning algorithm and effectively block the detected target object area. In the proposed method, only the target object containing the personal information is detected using a neural network-based learning algorithm. Then, a grid-like mosaic is created and overlapped on the target object area detected in the previous step, thereby effectively blocking the object area containing the personal information. Experimental results show that the proposed algorithm robustly detects the object area in which personal information is exposed and effectively blocks the detected area through mosaic processing. The object blocking method presented in this paper is expected to be useful in many applications related to computer vision.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1330-1339
• /
• 2022

3D object detection generally aims to detect relatively large data such as automobiles, buses, persons, furniture, etc, so it is vulnerable to small object detection. In addition, in an environment with limited resources such as embedded devices, it is difficult to apply the model because of the huge amount of computation. In this paper, the accuracy of small object detection was improved by focusing on local features using only one layer, and the inference speed was improved through the proposed knowledge distillation method from large pre-trained network to small network and adaptive quantization method according to the parameter size. The proposed model was evaluated using SUN RGB-D Val and self-made apple tree data set. Finally, it achieved the accuracy performance of 62.04% at mAP@0.25 and 47.1% at mAP@0.5, and the inference speed was 120.5 scenes per sec, showing a fast real-time processing speed.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.77-80
• /
• 2004

원화자로부터 목표 화자의 음성으로 변환을 위해서는 음운 및 피치변환이 이루어져야 한다. 원 음성과 목표 음성 신호 사이에 따른 발성길이, 크기 및 피치 등의 운율 특성은 화자의 개인성 및 발성문장의 의도를 나타내는 주요 역할을 한다. 본 논문에서는 음성 변환을 수행하기 위하여 발성된 음성의 강세구(phrase)단위의 피치 검출을 통하여 템플릿을 추출하는 방법을 제안한다. 우선 한국어의 운율구에 대한 정보가 필요한 것인지, 한국어는 어떤 운율 구조를 갖는지에 대하여 알아본다. 마지막으로 어떻게 연속음성으로부터 한국어에 적당한 운율구 단위를 나눌 것인지, 즉 자동 세그멘테이션 및 레이블링에 대하여 분석한다. 또한 논문에서는 한국어 문장음성의 운율구를 강세구와 억양구로 나누고 육안으로 표시한 운율구 단위를 기준으로 이 운율구 단위에 적합한 특징을 추출하여 패턴을 작성한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.177-179
• /
• 2021

This paper proposes a method of estimating location of a target point at which an interactive robot gazes in an indoor space. RGB images are extracted from low-cost web-cams, user head pose is obtained from the face detection (Openface) module, and geometric configurations are applied to estimate the user's gaze direction in the 3D space. The coordinates of the target point at which the user stares are finally measured through the correlation between the estimated gaze direction and the plane on the table plane.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.2
• /
• pp.370-376
• /
• 2022

Smart ships related studies are being conducted in various fields owing to the development of technology, and an engine room patrol robot that can patrol the unmanned engine room is one such study. A patrol robot moves around the engine room based on the information learned through artificial intelligence and checks the machine normality and occurrence of abnormalities such as water leakage, oil leakage, and fire. Study on engine room patrol robots is mainly conducted on machine detection using artificial intelligence, however study on movement and control is insufficient. This causes a problem in that even if a patrol robot detects an object, there is no way to move to the detected object. To secure maneuverability to quickly identify the presence of abnormality in the engine room, this study experimented with whether a patrol robot can determine the shortest path by applying the A* algorithm. Data were obtained by driving a small car equipped with LiDAR in the ship engine room and creating a map by mapping the obtained data with SLAM(Simultaneous Localization And Mapping). The starting point and arrival point of the patrol robot were set on the map, and the A* algorithm was applied to determine whether the shortest path from the starting point to the arrival point was found. Simulation confirmed that the shortest route was well searched while avoiding obstacles from the starting point to the arrival point on the map. Applying this to the engine room patrol robot is believed to help improve ship safety.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.63-71
• /
• 2021

Among drone autonomous flight technologies, obstacle avoidance is a very important technology that can prevent damage to drones or surrounding environments and prevent danger. Although the LiDAR sensor-based obstacle avoidance method shows relatively high accuracy and is widely used in recent studies, it has disadvantages of high unit price and limited processing capacity for visual information. Therefore, this paper proposes an obstacle avoidance algorithm for drones using camera-based PPO(Proximal Policy Optimization) reinforcement learning, which is relatively inexpensive and highly scalable using visual information. Drone, obstacles, target points, etc. are randomly located in a learning environment in the three-dimensional space, stereo images are obtained using a Unity camera, and then YOLov4Tiny object detection is performed. Next, the distance between the drone and the detected object is measured through triangulation of the stereo camera. Based on this distance, the presence or absence of obstacles is determined. Penalties are set if they are obstacles and rewards are given if they are target points. The experimennt of this method shows that a camera-based obstacle avoidance algorithm can be a sufficiently similar level of accuracy and average target point arrival time compared to a LiDAR-based obstacle avoidance algorithm, so it is highly likely to be used.

• 전기의세계
• /
• v.38 no.5
• /
• pp.68-77
• /
• 1989

Beam monitor는 beam이 발생하는 전장, 자장 또는 방사광등 beam에 의해 유기되는 ion을 관측하는 것과 같이 간접적으로 beam의 정보를 얻는 방법과 beam의 진로에 직접 sensor를 삽입해 전하입자로써의 beam과 장치를 구성하는 매질의 상호작용에 의해 정보를 얻는 방법으로 대변할 수 있다. monitor는 전극동의 검출기에 유기되는 신호level이 비교적 낮으므로 설계 제작시에는 대개의 경우 이론적인 계산을 그대로 설계에 적용할 수 있다. 따라서, 설계 제작시에는 동작원리등을 충분히 검토한 후에 설계해야 한다. monitor의 정도는 검출기의 기계설계와 회로설계의 적부에 의해 결정되기 때문이다. 한편 전자 beam에 의해 유기되는 전기적성질을 이용한 beam monitor에 비해 SR을 이용한 monitor의 경우에는 주위의 전기적인 noise의 영향을 전혀 받지 않는다는 점에 커다란 이점을 갖고 있다. PLS에서 목표로 하고 있는 제3세대 machine에서도 SR monitor는 중시되고 있다.