• 전자공학회논문지
• /
• 제52권8호
• /
• pp.132-139
• /
• 2015

카메라를 이용하는 시각(visual) SLAM(Simultaneous Localization And Mapping)은 로봇의 위치 등을 파악하는데 널리 이용되고 있다. 일반적으로 시각 SLAM은 움직임이 없는 고정된 특징점을 대상으로 연속적인 시퀀스 상에서 카메라의 움직임을 추정한다. 따라서 이동하는 객체가 많이 존재하는 상황에서는 안정적인 결과를 기대하기 어렵다. 본 논문에서는 이동 객체가 많은 상황에서 스테레오 카메라를 이용한 SLAM을 안정화하는 방법을 제안한다. 먼저, 스테레오 카메라를 이용하여 깊이영상을 추출하고 옵티컬 플로우를 계산한다. 그리고 좌우 영상의 옵티컬 플로우를 이용하여 시차변화(disparity change)를 계산한다. 그리고 깊이 영상에서 사람과 같이 움직이는 객체에 대한 ROI(Region Of Interest)를 구한다. 실내 상황에서는 벽과 같은 정적인 평면들이 움직이는 영역으로 잘못 판단되는 경우가 자주 발생한다. 이런 문제점을 해결하기 위해 깊이 영상을 X-Z 평면으로 사영하고 허프(hough) 변환하여 장면을 구성하는 평면을 결정한다. 앞의 과정에서 판단된 이동 객체 중에서 벽과 같은 장면 요소를 제외한다. 제안된 방법을 통해 정적인 특징점이 요구되는 SLAM의 성능을 보다 안정화할 수 있음을 확인하였다.

• 한국지능시스템학회논문지
• /
• 제24권3호
• /
• pp.259-264
• /
• 2014

본 연구는 자기 홀 센서의 특성으로 인해 실내 환경에서만 이용이 되었던 자기/자기-자이로유도 타입의 무인운반차를 실외 환경에서도 적용이 가능하도록 실외 주행용 자기 위치측정 장치를 설계 및 제작하는 것이다. 현재 이용되고 있는 자기 위치측정 장치는 측정 높이가 30mm로 바닥 환경이 고르고 평평한 실내 환경에 적합한 구조이다. 하지만 바닥 환경이 울퉁불퉁하거나 불균형적인 실외환경에 이용되는 무인운반차에는 부적합하다. 그 이유는 무인운반차 서스펜션이 부착되게 되고, 이 때 자기 위치측정 장치의 부착높이가 30mm 이하로 무인운반차에 가해진 충격으로 인해 장치와 바닥과의 충돌이 발생하게 되면 장치가 파손되기 때문이다. 따라서 실외 자기유도 무인운반차에 적용하기 위해서는 100mm 이상의 측정 높이를 가지는 자기 위치측정 장치가 필요하다. 현재 자기위치측정 장치의 성능 향상 및 개발에 관련된 다양한 연구들이 진행되었지만, 다양한 자기 홀 센서를 분석하여 본 논문에서는 자기위치측정 장치를 설계 및 제작하였고, 자기 홀 센서의 특성 정보를 이용한 특성 함수를 이용해 자성체의 위치를 검출하였다. 실험을 위하여 알루미늄을 이용한 실험 장비를 제작하였으며, 제안된 자기 위치측정 장치를 이용하여 실험한 결과 위치측정 정밀도 오차는 10mm 이하이고, 측정 높이는 평균 150mm 로 실외 자기유도 무인운반차에 적합한 것을 확인하였다.

• 전자공학회논문지SC
• /
• 제49권4호
• /
• pp.90-101
• /
• 2012

단일 카메라 기반의 SLAM(Simultaneous Localization and Mapping)을 성공적으로 수행하기 위해서는 표식 선택이 매우 중요하다. 특히, 미지의 환경에서는 표식에 대한 사정정보가 없기 때문에 표식을 자동 선택하는 기술이 필요하다. 본 논문에서는 표식을 자동 선택하기 위해 인간의 시각 집중 방식을 모델링한 시각 집중 시스템을 이용한다. 기존의 시각 집중 시스템에서 윤곽선(Edge)는 시각 집중을 위한 중요한 요소 중 하나이다. 하지만 복잡한 실내 환경에서 윤곽선의 응답을 사용할 경우 정규화 연산으로 인해 정보가 많은 복잡한 영역의 윤곽선에 대한 응답은 낮아지고 특징이 없는 평면이나 평면들 간의 경계에서 높은 값을 가지게 된다. 또한 네 방향에 대한 응답 값을 사용하기 때문에 특징의 차원수가 증가해서 연산량도 증가한다. 본 논문에서는 앞에서 언급한 문제점들을 해결하기 위해 모서리 특징의 사용을 제안한다. 모서리 특징을 사용함으로써 정보가 많은 복잡한 영역을 우선 집중시켜 데이터 연관(Data association)의 정확도도 높일 수 있다. 최종적으로는 코너특징을 사용한 시각 집중 시스템을 이용함으로써 기존 방식보다 SLAM 결과가 향상 된다는 것을 실험으로 보이도록 하겠다.

• 디자인학연구
• /
• 제19권3호
• /
• pp.183-194
• /
• 2006

It is expected that the typical lifestyle of the future will be transformed into an opulent and comfortable existence as the quality of life improves due to the increase in household income and reduction in working hours. In the meantime, as the standard of living becomes increasingly more comfortable and plentiful, the toll on physical health becomes magnified as a result of obesity and insufficient exercise caused by super nutrition and change in labor conditions. This has instigated a deep awareness in fitness on the part of many people, forcing them to recognize the significance of daily exercise and physical activity. The Elliptical Cross Trainer(ECT), which has drawn wide attention recently, is a non-impact athletic apparatus that not only promotes exercise of the upper body parts in such sports as skiing but also the exercise of lower parts of the body on a treadmill. It is a type of cross training athletic gear that has been developed for aerobic exercise throughout the entire body. It has already formed a market as big as that of the treadmill in Europe, America, etc. Recently, its demand is growing sharply in the Korean markets as well as those in Northeast Asian countries. Despite such demand increase and expansion, since most of the expensive ECTs are exclusively supplied by suppliers in only a few advanced countries, localization of the ECT is urgently required in order to enhance competitiveness of Korean manufacturers and to expand the market. The ECT development project has been in full swing for approximately two year since 2004 in order to secure independent design, as well as engineering and manufacturing processes in efforts to develop a commercially viable ECT.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.182-184
• /
• 2009

FlexRay는 차세대 차량 및 선박 내 전자 장치간의 통신을 위해 고속의 시리얼 통신, time triggered bus, fault tolerant 통신을 제공하는 새로운 네트워크 통신 시스템의 표준이다. FlexRay Communication Controller(CC)는 FlexRay 프로토콜 규격의 핵심 부분이다. 본 논문에서는 먼저 SDL(Specification and Description Language)를 이용하여 FlexRay CC 프로토콜 규격과 기능 부분을 설계한다. 다음 설계한 SDL 소스를 기반으로 Verilog HDL을 이용하여 하드웨어로 설계한다. 설계한 FlexRay CC는 Samsung $0.35{\mu}m$ 공정을 이용하여 합성하였으며, 그 결과 80 MHz의 속도로 동작하는 것으로 나타났다. 또한 FlexRay 시스템의 동작을 확인하기 위해 로봇에 적용되는 음원위치 추정 시스템에 응용하였다. 응용 시스템은 ALTERA Excalibur ARM EPAX4F672C3을 이용하여 검증하였으며 성공적으로 동작함을 확인하였다.

• 제어로봇시스템학회논문지
• /
• 제22권10호
• /
• pp.833-838
• /
• 2016

This paper presents a performance evaluation of various feature-initialization algorithms for forward-viewing mono-camera based simultaneous localization and mapping (SLAM), specifically in indoor environments. For mono-camera based SLAM, the position of feature points cannot be known from a single view; therefore, it should be estimated from a feature initialization method using multiple viewpoint measurements. The accuracy of the feature initialization method directly affects the accuracy of the SLAM system. In this study, four different feature initialization algorithms are evaluated in simulations, including linear triangulation; depth parameterized, linear triangulation; weighted nearest point triangulation; and particle filter based depth estimation algorithms. In the simulation, the virtual feature positions are estimated when the virtual robot, containing a virtual forward-viewing mono-camera, moves forward. The results show that the linear triangulation method provides the best results in terms of feature-position estimation accuracy and computational speed.

• 로봇학회논문지
• /
• 제7권3호
• /
• pp.205-215
• /
• 2012

A GPS sensor is widely used in many areas such as navigation, or air traffic control. Particularly, the car navigation system is equipped with GPS sensor for locational information. However, when a car goes through a tunnel, forest, or built-up area, GPS receiver cannot get the enough number of satellite signals. In these situations, a GPS receiver does not reliably work. A GPS error can be formulated by sum of bias error and sensor noise. The bias error is generated by the geometric arrangement of satellites and sensor noise error is generated by the corrupted signal noise of receiver. To enhance GPS sensor accuracy, these two kinds of errors have to be removed. In this research, we make the road database which includes Road Database File (RDF). RDF includes road information such as road connection, road condition, coordinates of roads, lanes, and stop lines. Among the information, we use the stop line coordinates as a feature point to correct the GPS bias error. If the relative distance and angle of a stop line from a car are detected and the detected stop line can be associated with one of the stop lines in the database, we can measure the bias error and correct the car's location. To remove the other GPS error, sensor noise, the Kalman filter algorithm is used. Additionally, using the RDF, we can get the information of the road where the car belongs. It can be used to help the GPS correction algorithm or to give useful information to users.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권11호
• /
• pp.4084-4104
• /
• 2021

Visual place recognition (VPR) is a fundamental yet challenging task of mobile robot navigation and localization. The existing VPR methods are usually based on some pairwise similarity of image descriptors, so they are sensitive to visual appearance change and also computationally expensive. This paper proposes a simple yet effective four-step method that achieves adaptive convolutional neural network (CNN) landmark matching for VPR. First, based on the features extracted from existing CNN models, the regions with higher significance scores are selected as landmarks. Then, according to the coordinate positions of potential landmarks, landmark matching is improved by removing mismatched landmark pairs. Finally, considering the significance scores obtained in the first step, robust image retrieval is performed based on adaptive landmark matching, and it gives more weight to the landmark matching pairs with higher significance scores. To verify the efficiency and robustness of the proposed method, evaluations are conducted on standard benchmark datasets. The experimental results indicate that the proposed method reduces the feature representation space of place images by more than 75% with negligible loss in recognition precision. Also, it achieves a fast matching speed in similarity calculation, satisfying the real-time requirement.

• 드라이브 ㆍ 컨트롤
• /
• 제20권4호
• /
• pp.1-8
• /
• 2023

In recent years, robots have been utilized in various industries to reduce workload and enhance work efficiency. The following mobility offers users convenience by autonomously tracking specific locations and targets without the need for additional equipment such as forklifts or carts. In this paper, deep learning techniques were employed to recognize individuals and assign each of them a unique identifier to enable the recognition of a specific person even among multiple individuals. To achieve this, the distance and angle between the robot and the targeted individual are transmitted to respective controllers. Furthermore, this study explored the control methodology for mobility that tracks a specific person, utilizing Simultaneous Localization and Mapping (SLAM) and Proportional-Integral-Derivative (PID) control techniques. In the PID control method, a genetic algorithm is employed to extract the optimal gain value, subsequently evaluating PID performance through simulation. The SLAM method involves generating a map by synchronizing data from a 2D LiDAR and a depth camera using Real-Time Appearance-Based Mapping (RTAB-MAP). Experiments are conducted to compare and analyze the performance of the two control methods, visualizing the paths of both the human and the following mobility.

• 국제학술발표논문집
• /
• The 10th International Conference on Construction Engineering and Project Management
• /
• pp.152-159
• /
• 2024

Cracks in structural materials present a critical challenge to infrastructure safety and long-term durability. Timely and precise crack detection is essential for proactive maintenance and the prevention of catastrophic structural failures. This study introduces an innovative approach to tackle this issue using U-Net deep learning architecture. The primary objective of the intended research is to explore the potential of U-Net in enhancing the precision and efficiency of crack detection across various concrete crack detection under various environmental conditions. Commencing with the assembling by a comprehensive dataset featuring diverse images of concrete cracks, optimizing crack visibility and facilitating feature extraction through advanced image processing techniques. A wide range of concrete crack images were collected and used advanced techniques to enhance their visibility. The U-Net model, well recognized for its proficiency in image segmentation tasks, is implemented to achieve precise segmentation and localization of concrete cracks. In terms of accuracy, our research attests to a substantial advancement in automated of 95% across all tested concrete materials, surpassing traditional manual inspection methods. The accuracy extends to detecting cracks of varying sizes, orientations, and challenging lighting conditions, underlining the systems robustness and reliability. The reliability of the proposed model is measured using performance metrics such as, precision(93%), Recall(96%), and F1-score(94%). For validation, the model was tested on a different set of data and confirmed an accuracy of 94%. The results shows that the system consistently performs well, even with different concrete types and lighting conditions. With real-time monitoring capabilities, the system ensures the prompt detection of cracks as they emerge, holding significant potential for reducing risks associated with structural damage and achieving substantial cost savings.