• Journal of information and communication convergence engineering
• /
• 제19권3호
• /
• pp.188-197
• /
• 2021

In military operations, an accurate localization system is required to navigate soldiers to their destinations, even in non-GPS environments. The global positioning system is a commonly used localization method, but it is difficult to maintain the robustness of GPS-based localization against jamming of signals. In addition, GPS-based localization cannot provide important terrain information such as obstacles. With the widespread use of embedded sensors, sensor-based pedestrian tracking schemes have become an attractive option. However, because of noisy sensor readings, pedestrian tracking systems using motion sensors have a major drawback in that errors in the estimated displacement accumulate over time. We present a group-based standalone system that creates terrain maps automatically while also locating soldiers in mountainous terrain. The system estimates landmarks using inertial sensors and utilizes split group information to improve the robustness of map construction. The evaluation shows that our system successfully corrected and combined the drift error of the system localization without infrastructure.

• 한국산업융합학회 논문집
• /
• 제22권4호
• /
• pp.459-465
• /
• 2019

There is an increasing interest in health and research on methods for measuring human body information. The importance of continuously observing information such as the step change and the walking speed is increasing. At a person's gait, information about the disease and the currently weakened area can be known. In this paper, gait is measured using wearable walking module built in shoes. We want to make continuous measurement possible by simplifying gait measurement method. This module is designed to receive information of gyro sensor and acceleration sensor. The designed module is capable of WiFi communication and the collected walking information is stored in the server. The information stored in the server is corrected by integrating the acceleration sensor and the gyro sensor value. A band-pass filter was used to reduce the error. This data is categorized by the Gait Finder into walking and waiting states. When walking, each step is divided and stored separately for analysis.

• 대한임베디드공학회논문지
• /
• 제8권4호
• /
• pp.185-194
• /
• 2013

Abstract- In distant-talking environments, speech recognition performance degrades significantly due to noise and reverberation. Recent work of Michael L. Selzer shows that in microphone array speech recognition, the word error rate can be significantly reduced by adapting the beamformer weights to generate a sequence of features which maximizes the likelihood of the correct hypothesis. In this approach, called Likelihood Maximizing Beamforming algorithm (Limabeam), one of the method to implement this Limabeam is an UnSupervised Limabeam(USL) that can improve recognition performance in any situation of environment. From our investigation for this USL, we could see that because the performance of optimization depends strongly on the transcription output of the first recognition step, the output become unstable and this may lead lower performance. In order to improve recognition performance of USL, some post-filter techniques can be employed to obtain more correct transcription output of the first step. In this work, as a post-filtering technique for first recognition step of USL, we propose to add a Wiener-Filter combined with Feature Weighted Malahanobis Distance to improve recognition performance. We also suggest an alternative way to implement Limabeam algorithm for Hidden Markov Network (HM-Net) speech recognizer for efficient implementation. Speech recognition experiments performed in real distant-talking environment confirm the efficacy of Limabeam algorithm in HM-Net speech recognition system and also confirm the improved performance by the proposed method.

• 대한수학교육학회지:수학교육학연구
• /
• 제16권2호
• /
• pp.157-177
• /
• 2006

비와 비례 개념은 독립적으로 발달하는 것이 아니다. 오히려 이런 개념은 곱셈적 개념 장의 일부분으로 서로 관련을 가지면서 발달하게 된다. 곱셈적 개념 장에는 곱셈, 나눗셈, 분수, 비, 유리수와 같은 개념을 포함한다. 본 연구에서는 이런 개념의 발달 과정이 어떻게 시작하는가를 알아보기 위한 목적으로, 한 초등학교 4학년 아동을 대상으로 비례추론 과제를 해결하는 실험 수업을 실행하였다. 연구를 통해 이 아동이 비형식적 전략을 전개하면서 어떤 도전에 직면하였는지 그리고 비와 비례 개념을 전개하면서 어떤 수학적 지식이 유용하였는지를 분석할 수 있었다. 이러한 연구 결과는 비와 비례 개념의 발달은 곱셈적 개념 장의 발달과 깊은 관계가 있다는 기존의 입장을 지지하는 것으로 나타났다.

• 한국정보통신학회논문지
• /
• 제13권7호
• /
• pp.1312-1320
• /
• 2009

본 논문은 Particle Swarm Optimization(PSO)을 이용하여 2차원 IIR 디지털필터의 설계방법을 제안하였다. 먼저 2차원 디지털필터의 설계문제를 PSO에 적용하기 위하여 최소화 문제로써 형식화 과정이 논의된다. 제안된 PSO 알고리즘을 이용한 설계방법은 기존의 PSO 알고리즘에 IIR 필터설계에서 요구되는 안정성을 보증하는 과정이 검토되어 개선된다. 본 논문에서 제안된 방법의 타당성을 설계예시를 통해 고찰한 결과, 설계된 디지털필터는 동일한 설계사양으로 기존의 설계방법으로 설계된 디지털필터보다 근사오차 면에서 우수한 결과를 얻을 수 있었다. 또한 제안한 설계방법에 의한 2차원 IIR 디지털필터는 설계과정에서 필터의 안정성을 보증할 수 있었다.

• 정보처리학회논문지B
• /
• 제9B권3호
• /
• pp.351-358
• /
• 2002

DCT(Discrete Cosine Transform) 기반 동영상 압축 기법은 블록화 현상과 해상도 변화 시 픽셀의 손상이 생기는 단점이 있다. DWT(Discrete Wavelet Transform)을 기반한 기법은 이러한 문제점을 극복할 수 있다. Wavelet을 기반한 동영상 부호화 기법 중 하나인 SAMCoW(Scalable Adaptive Motion Compensation Wavelet)에서 화면내 부호화와 움직임 보상된 오차 영상은 EZW(Embedded Zerotree Wavelet) 부호화 방식으로 부호화한다. 그러나 움직임 보상된 오차 영상의 wavelet 변환 계수의 특성은 정지 영상의 wavelet 변환 계수의 특성과는 다르다. 신호의 에너지는 대부분의 정지 영상의 경우와는 달리 저주파 대역에 집중되지 않고 오히려 모든 주파수 대역에 고르게 분포한다. 본 논문에서는 이러한 특성을 이용한 새로운 동영상 부호화 방식을 제안하였다. EZW 부호화 대신 고주파 성분이 많이 포함된 영상의 부호화에 효율적이며 계수사이의 대역별 상관관계에 의존하지 않는 공간 부호화를 화면내 부호화와 화면간 부호화에 적용하였다. 공간 부호화는 EZW와는 달리 wavelet 분해를 통해 얻어진 각 대역을 대역간의 상관 관계를 이용하지 않으면서 각 대역내의 중요 계수의 존재 여부와 위치를 점진적으로 부호화하는 기법이다. Wavelet 기반 동영상 부호화에 EZW 부호화 대신 공간 부호화를 적용하였을 때 우수한 성능을 나타내었다.

• Journal of Biosystems Engineering
• /
• 제38권4호
• /
• pp.255-263
• /
• 2013

Purpose: It is not easy to drive a rice-transplanter avoiding underlapped or overlapped transplanting in paddy fields. An automated guidance system for the riding-type rice-transplanter would be necessary to operate the rice-transplanter autonomously or to assist the beginning drivers as a driving aid. Methods: A prototype of guidance system was composed of embedded computers, RTK-GPS, and a power-steering mechanism. Two Kalman filters were adopted to overcome sparse positioning data (1 Hz) from the RTK-GPS. A global Kalman filter estimated the posture of rice-transplanter every one second, and a local Kalman filter calculated the posture from every new estimation of the global Kalman filter with an interval of 200 ms. A PID controller was applied to the row-following mode control. A control method of U-turning mode was developed as well. A stepping motor with a reduction gear set was used to rotate the shaft of steering wheel. Results: Test trials for U-turning and row-following modes were done in a paddy field after some parameters have been tuned at the ground speed range of 0.3 ~ 1.2 m/s. The minimum RMS error of offset was 3.13 cm at the ground speed of 0.3 m/s while the maximum RMS error was 13.01 cm at 1.2 m/s. The offset RMS error tended to increase as the ground speed increased. The target point distance, LT also affected the system performance and PID controller parameters should be adjusted on different ground speeds. Conclusions: A target angle-based PID controller plus stationary steering angle controller made it possible for the rice-transplanter to steer autonomously by following a reference line accurately and even on U-turning mode. However, as condition in paddy fields is very complicated, the system should control the ground speed that prevents it from deviating too much due to ditch and slope.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1458-1463
• /
• 2004

Tracking is one of the most important pre-required task for many application such as human-computer interaction through gesture and face recognition, motion analysis, visual servoing, augment reality, industrial assembly and robot obstacle avoidance. Recently, 3D information of object is required in realtime for many aforementioned applications. 3D tracking is difficult problem to solve because during the image formation process of the camera, explicit 3D information about objects in the scene is lost. Recently, many vision system use stereo camera especially for 3D tracking. The 3D feature based tracking(3DFBT) which is on of the 3D tracking system using stereo vision have many advantage compare to other tracking methods. If we assumed the correspondence problem which is one of the subproblem of 3DFBT is solved, the accuracy of tracking depends on the accuracy of camera calibration. However, The existing calibration method based on accurate camera model so that modelling error and weakness to lens distortion are embedded. Therefore, this thesis proposes 3D feature based tracking method using SVM which is used to solve reconstruction problem.

• Corrosion Science and Technology
• /
• 제18권6호
• /
• pp.253-257
• /
• 2019

A deep learning based real-time painting surface inspection algorithm is proposed herein, designed for developing an autonomous inspection drone. The painting surface inspection is usually conducted manually. However, the manual inspection has a limitation in obtaining accurate data for correct judgement on the surface because of human error and deviation of individual inspection experiences. The best method to replace manual surface inspection is the vision-based inspection method with a camera, using various image processing algorithms. Nevertheless, the visual inspection is difficult to apply to surface inspection due to diverse appearances of material, hue, and lightning effects. To overcome technical limitations, a deep learning-based pattern recognition algorithm is proposed, which is specialized for painting surface inspections. The proposed algorithm functions in real time on the embedded board mounted on an autonomous inspection drone. The inspection results data are stored in the database and used for training the deep learning algorithm to improve performance. The various experiments for pre-inspection of painting processes are performed to verify real-time performance of the proposed deep learning algorithm.

• Journal of the Optical Society of Korea
• /
• 제5권4호
• /
• pp.140-145
• /
• 2001

We present a new method of volumetric interferometer, which is intended to measure the three-dimensional coordinates of a moving object in a simultaneous way with a single optical setup. The method is based on the principles of phase-measuring interferometry with phase shifting. Two diffraction point sources, which are made of the polished ends of single-mode optical fibers are embedded on the object. Two spherical wavefronts emanate from the diffraction point sources and interfere with each other within the measurement volume. One wavefront is phase-shifted by elongating the corresponding fiber using a PZT extender. A CCD array sensor fixed at the stationary measurement station detects the resulting interference field. The measured phases are then related to the three-dimensional location of the object with a set of non-liner equations of Euclidean distance, from which the complete set of three-dimensional spatial coordinates of the object is determined through rigorous numerical computation based upon the least square error minimization.