• 한국정밀공학회지
• /
• 제16권1호통권94호
• /
• pp.253-264
• /
• 1999

Most autonomous mobile robots view only things in front of them, and as a result, they may collide with objects moving from the side or behind. To overcome this problem. an Active Omni-directional Range Sensor System has been built that can obtain an omni-directional range data through the use of a laser conic plane and a conic mirror. Also, mobile robot has to know its current location and heading angle by itself as accurately as possible to successfully navigate in real environments. To achieve this capability, we propose a self-localization algorithm of a mobile robot using an active omni-directional range sensor in an unknown environment. The proposed algorithm estimates the current position and head angle of a mobile robot by a registration of the range data obtained at two positions, current and previous. To show the effectiveness of the proposed algorithm, a series of simulations was conducted and the results show that the proposed algorithm is very efficient, and can be utilized for self-localization of a mobile robot in an unknown environment.

• Journal of Computing Science and Engineering
• /
• 제5권3호
• /
• pp.161-166
• /
• 2011

We present a fast algorithm for Korean text extraction and segmentation from subway signboards using smart phone sensors in order to minimize computational time and memory usage. The algorithm can be used as preprocessing steps for optical character recognition (OCR): binarization, text location, and segmentation. An image of a signboard captured by smart phone camera while holding smart phone by an arbitrary angle is rotated by the detected angle, as if the image was taken by holding a smart phone horizontally. Binarization is only performed once on the subset of connected components instead of the whole image area, resulting in a large reduction in computational time. Text location is guided by user's marker-line placed over the region of interest in binarized image via smart phone touch screen. Then, text segmentation utilizes the data of connected components received in the binarization step, and cuts the string into individual images for designated characters. The resulting data could be used as OCR input, hence solving the most difficult part of OCR on text area included in natural scene images. The experimental results showed that the binarization algorithm of our method is 3.5 and 3.7 times faster than Niblack and Sauvola adaptive-thresholding algorithms, respectively. In addition, our method achieved better quality than other methods.

• 제어로봇시스템학회논문지
• /
• 제13권1호
• /
• pp.39-45
• /
• 2007

This paper proposes a method of container position measurement using automatic landing system that is estimated by a laser range finder. In the most of container position measurement methods, CCD cameras or laser scanners have been used to get the source data. However those sensors are not only weak for disturbances, for examples, the light, fog, and rain, but also the system cost is high. When the spreader arrives at the goal position, it is still swung by inertia or by wind effect. In this paper, the spreader swung data have been used to find the container position. The laser range finder is equipped in the front side of spreader. It can measure distance and relative position between spreader and container. This laser range finder can be rotated as desired by a motor. And a tilt sensor is equipped on the spreader to measure spreader sway. The relative position information between the spreader and a container using the laser range finder and tilt sensor is estimated through the geometrical analysis.

• Geomechanics and Engineering
• /
• 제14권3호
• /
• pp.257-269
• /
• 2018

Analysis of slope stability failures, as one of the complex natural hazards, is one of the important research issues in the field of civil engineering. Present paper adopts and investigates four soft computing-based techniques for this problem: Patient Rule-Induction Method (PRIM), M5' algorithm, Group Method of data Handling (GMDH) and Multivariate Adaptive Regression Splines (MARS). A comprehensive database consisting of 168 case histories is used to calibrate and test the developed models. Six predictive variables including slope height, slope angle, bulk density, cohesion, angle of internal friction, and pore water pressure ratio were considered to generate new models. The results of test studies are used for feasibility, effectiveness and practicality comparison of techniques with each other, and with the other available well-known methods in the literature. Results show that all methods not only are feasible but also result in better performance than previously developed soft computing based predictive models and tools. It is shown that M5' and PRIM algorithms are the most effective and practical prediction models.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제6권1호
• /
• pp.29-36
• /
• 2017

본 논문에서는 손목형 가속도계를 이용하여 운동 가속도가 거의 없는 식사 행동을 인식하기 위한 방법을 제안한다. 먼저 손목 방향에 작용하는 중력 가속도를 이용하여 중력 방향과 손목 방향 간의 각도를 구하고, 특정 각도 영역에서 첨두값과 첨미값이 존재하는 경우 손목이 왕복하는 동작을 검출한다. 손목 왕복 동작 발생 횟수를 누적하여 그 횟수가 10회 이상일 경우 검출 시점으로 5분 전까지 식사 시간으로 간주하며, 그 지속시간이 7분 이상인 경우에만 식사 시간으로 추론한다. 대학원생 4명으로부터 수집한 2128분 데이터를 통해 식사 시간을 추론한 결과 95.63%의 정확도를 보인다.

• 로봇학회논문지
• /
• 제19권1호
• /
• pp.130-138
• /
• 2024

High-precision 3D Object Detection is a crucial component within autonomous driving systems, with far-reaching implications for subsequent tasks like multi-object tracking and path planning. In this paper, we propose a novel approach designed to enhance the performance of 3D Object Detection, especially in heading angle estimation by employing a moving object segmentation technique. Our method starts with extracting point-wise moving labels via a process of moving object segmentation. Subsequently, these labels are integrated into the LiDAR Pointcloud data and integrated data is used as inputs for 3D Object Detection. We conducted an extensive evaluation of our approach using the KITTI-road dataset and achieved notably superior performance, particularly in terms of AOS, a pivotal metric for assessing the precision of 3D Object Detection. Our findings not only underscore the positive impact of our proposed method on the advancement of detection performance in lidar-based 3D Object Detection methods, but also suggest substantial potential in augmenting the overall perception task capabilities of autonomous driving systems.

• 한방재활의학과학회지
• /
• 제32권1호
• /
• pp.63-72
• /
• 2022

Objectives This study was conducted to characterize scoliosis patients visiting Korean medicine hospital and to analyze the demands and factors affecting discomfort. Methods This retrospective study analyzed 33 scoliosis patients who visited Korean medicine hospital from March, 2021 to October, 2021. The data analysis consisted of three factors: (1) demographic characteristics, (2) characteristics of demands on Korean medicine (reasons for choosing Korean medical treatment, preferred treatment methods, most uncomfortable part, treatment priorities) and (3) discomfort factors (treatment experiences, diagnosed age and Cobb's angle). Statistical analyses were performed and a p-value≤0.05 was considered to be statistically significant. Results 43.75% of the patients chose 'effectiveness' for the reason why they preferred Korean medicine treatment. 'Chuna treatment' was the most preferred treatment method. The patients chose 'lower back' for the most uncomfortable part and 'pain' for the highest priority of improvement. The Cobb's angle of included patients was 16.02±7.65° and it is not much differ to average of Cobb's angle in Korean. Discomfort was more severe in the patients with treatment-experienced than treatment-naive. The score of discomfort in appearance and psychological were higher in the patients diagnosed in childhood or adolescent period than who were diagnosed after adult. Classification based on Cobb's angle showed no statistical difference. Conclusions Not only Cobb's angle but also other clinical factors should be considered for effective treatment in scoliosis. Also, It is necessary to pay attention to adult scoliosis patients.

• 디자인학연구
• /
• 제17권4호
• /
• pp.141-148
• /
• 2004

본 논문은 스텝 애니메이션에서 표현되어지는 감성을 정의하고, 스텝 관련 감성 자극 요소들을 추출 측정, 분석하여 스텝의 직관적인 감성 표현을 정량화시키는 것을 목적으로 하고 있다. 실험 방법으로는 스텝 관련 27개의 감성 표현 어휘와 36개의 샘플 스텝 동영상의 상관관계를 설문 조사하였다. 통합된 데이터를 수량화 이론 III류를 이용하여 스텝의 감성적 멘털구조를 2차원 평면화 하였다. 이를 분석한 결과, 감성 스텝은 가로의 자신감 축과 세로의 안정감 축으로 형성되어 있음을 밝혀내었다. 감성 스텝의 2차원 분포도를 분석한 결과, <자신감, 불안감 쪽> 2사분면과 <자신감, 안정감 쪽> 3사분면은 데이터가 풍부한 반면 <소심함, 불안감 쪽> 1사분면과 <소심함, 안정감 쪽> 4사분면의 데이터 분포가 희박함을 보여주었다. 이러한 그래프 분석을 통해 불안감이 느껴지면서 소심한 감성과 안정감이 느껴지는 소심한 캐릭터의 감성은 스텝만으로 표현하기에는 난해한 감성 표현임을 파악할 수 있었다. 감성에 영향을 미치는 스텝의 신체 물리적 요소로는 <스텝의 간격> <스텝의 속도> <골반(Y축)의 움직임 각도> <팔 스윙 폭> <척추(x축)의 움직임 각도> <신체의 기울기> 6가지로 선정하여 분석하였다. 그 결과 <스텝의 속도>와 <신체의 기울기>가 스텝의 감성 자극에 가장 큰 영향을 미치는 요소임을 밝혀낼 수 있었다. 본 연구를 통해 캐릭터의 미묘한 감성 상태를 스텝 애니메이션에 자연스럽게 표현해 내는 과정에 있어 애니메이터들의 주관적인 가성 표현들을 객관화, 정량화시키고자 하였으며 향후 이 데이터들을 활용한 멀티컨텐츠의 적용을 목표로 하고 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.142-145
• /
• 2003

Many control applications using Neural Network need a priori information about the objective system. But it is impossible to get exact information about the objective system in real world. To solve this problem, several control methods were proposed. Reinforcement learning control using neural network is one of them. Basically reinforcement learning control doesn't need a priori information of objective system. This method uses reinforcement signal from interaction of objective system and environment and observable states of objective system as input data. But many methods take too much time to apply to real-world. So we focus on faster learning to apply reinforcement learning control to real-world. Two data types are used for reinforcement learning. One is reinforcement signal data. It has only two fixed scalar values that are assigned for each success and fail state. The other is observable state data. There are infinitive states in real-world system. So the number of observable state data is also infinitive. This requires too much learning time for applying to real-world. So we try to reduce the number of observable states by classification of states with Self-Organizing Map. We also use neural dynamic programming for controller design. An inverted pendulum on the cart system is simulated. Failure signal is used for reinforcement signal. The failure signal occurs when the pendulum angle or cart position deviate from the defined control range. The control objective is to maintain the balanced pole and centered cart. And four states that is, position and velocity of cart, angle and angular velocity of pole are used for state signal. Learning controller is composed of serial connection of Self-Organizing Map and two Multi-layer Feed-Forward Neural Networks.

• Journal of Biosystems Engineering
• /
• 제16권3호
• /
• pp.228-238
• /
• 1991

Cam plays very important roles due to continuous requirement for the high-speed and automation of the machinery. A large number of studies of cam curve were carried out by many researchers, and CNC milling and machining center for manufacturing cam have been widely used recently. The purpose of this study was to develop a CAD/CAM system for cam using QuickBasic language in 16-bit PC for application of cam design and manufacturing. Results obtained were as follows : 1. It was possible to input data by entering cam angle and its corresponding R, from 0 to 360 deg. of cam angle. The tediousness at entering data was minimized because of the same data format for both cylindrical cam and disc cam, and free format used for data file. 2. It was possible to design cam by choosing only the number of cam curve because of developing the CAD/CAM program with dimensionless method of cam curves including widely used 19 kinds. After selecting the number of the cam curve, the CAD/CAM system automatically shows the characteristics of cam motion enough to help a designer to decide : displacement, velocity, acceleration and jerk. 3. It was possible to execute, in an efficient way, both the cam profile synthesis and the generation of NC program for CNC machining center by using the input data. 4. This NC program generated by the CAD/CAM system developed here, was evaluated as positive in relation with actual manufacturing experiments and thought to be useful in its application without any modification. It can be said that this CAD/CAM system could be used by the beginners to design and manufacture the cam automatically as the system consists of very simple dialogue methods. In addition, self-developed QuickBasic would be would used as a basic tool for further stuides in this area of research, together with application.