• Journal of Mechanical Science and Technology
• /
• 제19권spc1호
• /
• pp.473-480
• /
• 2005

A three axes marine satellite antenna has been developed. As a design step, a CAD model for the antenna has been created according to the design requirements. Kinematic analyses are carried out to insure design specification and to check collision detection of the CAD model. Marine satellite antennas experience base motions, and a relevant control system should control the three antenna axis to point to the satellites accurately. A sensor fusion algorithm and a PIDA (Proportional, Integral, Derivative, Acceleration) control algorithm are designed and implemented to control the yaw, level, and cross-level angle of a small size satellite marine antenna. Antenna stabilization control experiments are performed using a test simulator which gives the antenna base motions. Experimental results show small pointing errors, which is less than 0.2 degree for the level, cross-level, and yaw axis.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2002년도 춘계공동학술대회
• /
• pp.266-271
• /
• 2002

We propose a hardware accelerated voxelization method for various 3D object model such as surface models, solid models, and volumetric CSG models. The algorithm utilizes the stencil buffer that is one of modern Open히 graphics hardware features. The stencil buffer is originally used to restrict drawing to certain portions of the screen. The volumetric representations of given 3D objects are constructed slice-by-slice. For each slice, the algorithm restricts the drawing areas constructed inner region of 3D objects using the stencil buffer, and generates slices of the volumetric representation for target objects. As a result, we can provide volume graphics support for various engineering applications such as multi-axis machining simulation, collision detection and finite element analysis.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2014년도 추계학술대회
• /
• pp.890-893
• /
• 2014

본 논문에서는 자동적으로 충돌을 예방하는 선박용 레이더 시스템의 표적 탐지 및 추적 알고리즘, 충돌위험 계산 및 위험 경보 알고리즘을 개발하고 이를 적용시켜 일련의 동작을 수행하는 신호처리 보드부를 디지털 하드웨어적으로 구현하였다. 근거리에서 성능이 우수한 FMCW (Frequency Modulation Continuous Wave) 신호를 송신신호로 사용하고 1도 간격으로 빔포밍하는 기계식 스캔방식의 안테나 사용을 시뮬레이션 환경으로 설정하였다. 테스트보드는 DSP칩, FPGA 등으로 구성되며 이를 이용하여 개발된 알고리즘의 시뮬레이션을 수행하는 임베디드 시스템을 구현하였다.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.1243-1244
• /
• 2022

In recent years, the growing interest in off-site construction has led to factories scaling up their manufacturing and production processes in the construction sector. Consequently, continuous large-scale site monitoring in low-variability environments, such as prefabricated components production plants (precast concrete production), has gained increasing importance. Although many studies on computer vision-based site monitoring have been conducted, challenges for deploying this technology for large-scale field applications still remain. One of the issues is collecting and transmitting vast amounts of video data. Continuous site monitoring systems are based on real-time video data collection and analysis, which requires excessive computational resources and network traffic. In addition, it is difficult to integrate various object information with different sizes and scales into a single scene. Various sizes and types of objects (e.g., workers, heavy equipment, and materials) exist in a plant production environment, and these objects should be detected simultaneously for effective site monitoring. However, with the existing object detection algorithms, it is difficult to simultaneously detect objects with significant differences in size because collecting and training massive amounts of object image data with various scales is necessary. This study thus developed a large-scale site monitoring system using edge computing and a small-object detection system to solve these problems. Edge computing is a distributed information technology architecture wherein the image or video data is processed near the originating source, not on a centralized server or cloud. By inferring information from the AI computing module equipped with CCTVs and communicating only the processed information with the server, it is possible to reduce excessive network traffic. Small-object detection is an innovative method to detect different-sized objects by cropping the raw image and setting the appropriate number of rows and columns for image splitting based on the target object size. This enables the detection of small objects from cropped and magnified images. The detected small objects can then be expressed in the original image. In the inference process, this study used the YOLO-v5 algorithm, known for its fast processing speed and widely used for real-time object detection. This method could effectively detect large and even small objects that were difficult to detect with the existing object detection algorithms. When the large-scale site monitoring system was tested, it performed well in detecting small objects, such as workers in a large-scale view of construction sites, which were inaccurately detected by the existing algorithms. Our next goal is to incorporate various safety monitoring and risk analysis algorithms into this system, such as collision risk estimation, based on the time-to-collision concept, enabling the optimization of safety routes by accumulating workers' paths and inferring the risky areas based on workers' trajectory patterns. Through such developments, this continuous large-scale site monitoring system can guide a construction plant's safety management system more effectively.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제14권8호
• /
• pp.818-822
• /
• 2008

본 논문에서는 가상환경에서 페인트를 분사하여 시간으로 물체를 도색 하는 시뮬레이션을 위한 충돌처리 및 시각화 알고리즘을 제시한다. 이를 통하여 물체에 페인트가 뿌려지면서 도색 되는 모습을 사실적으로 표현해 줄뿐만 아니라, 페인트 누적 모델을 이용하여 물체에 누적된 페인트의 두께 정보까지 시뮬레이션 하여 시각화함으로써 가상훈련 시스템에 적용할 수 있도록 한다. 분사되는 유체시뮬레이션을 위해서 기존에는 파티클 시스템이 이용되고 있으나 실시간으로 도색이 되는 과정을 시각화하기 위해서는 수백만 개의 파티클에 대하여 충돌 검사를 수행해야 하기 때문에 적절하지 않다. 따라서 본 연구에서는 소수의 레이와 텍스처 기법을 이용하여 효율적으로 충돌 검사를 수행하는 알고리즘을 제안하고 이를 구현하였으며 실시간 페인트 시뮬레이션 구현 결과와 수행 시간 분석을 통하여 알고리즘의 효율성을 검증하였다.

• 한국정밀공학회지
• /
• 제31권3호
• /
• pp.233-241
• /
• 2014

This paper contributes to development of a new method for detecting rear-side vehicles and estimating the positions for blind spot region or providing the lane change information by using vision systems. Because the real image acquired during car driving has a lot of information including the target vehicle and background image as well as the noises such as lighting and shading, it is hard to extract only the target vehicle against the background image with satisfied robustness. In this paper, the target vehicle has been detected by repetitive image processing such as sobel and morphological operations and a Kalman filter has been also designed to cancel the background image and prevent the misreading of the target image. The proposed method can get faster image processing and more robustness rather than the previous researches. Various experiments were performed on the highway driving situations to evaluate the performance of the proposed algorithm.

• 한국산업융합학회 논문집
• /
• 제24권5호
• /
• pp.547-553
• /
• 2021

Dynamic object recognition is an important task for autonomous vehicles. Since dynamic objects exhibit a higher collision risk than static objects, our own trajectories should be planned to match the future state of moving elements in the scene. Time information such as optical flow can be used to recognize movement. Existing optical flow calculations are based only on camera sensors and are prone to misunderstanding in low light conditions. In this regard, to improve recognition performance in low-light environments, we applied a normalization filter and a correction function for Gamma Value to the input images. The low light quality improvement algorithm can be applied to confirm the more accurate detection of Object's Bounding Box for the vehicle. It was confirmed that there is an important in object recognition through image prepocessing and deep learning using YOLO.

• Smart Structures and Systems
• /
• 제23권4호
• /
• pp.359-371
• /
• 2019

As part of a structural health monitoring system, the relative geometric relationship between a ship and bridge has been recognized as important for bridge authorities and ship owners to avoid ship-bridge collision. This study proposes a novel computer vision method for the real-time geometric parameter identification of moving ships based on a single shot multibox detector (SSD) by using transfer learning techniques and monocular vision. The identification framework consists of ship detection (coarse scale) and geometric parameter calculation (fine scale) modules. For the ship detection, the SSD, which is a deep learning algorithm, was employed and fine-tuned by ship image samples downloaded from the Internet to obtain the rectangle regions of interest in the coarse scale. Subsequently, for the geometric parameter calculation, an accurate ship contour is created using morphological operations within the saturation channel in hue, saturation, and value color space. Furthermore, a local coordinate system was constructed using projective geometry transformation to calculate the geometric parameters of ships, such as width, length, height, localization, and velocity. The application of the proposed method to in situ video images, obtained from cameras set on the girder of the Wuhan Yangtze River Bridge above the shipping channel, confirmed the efficiency, accuracy, and effectiveness of the proposed method.

• 대한임베디드공학회논문지
• /
• 제7권4호
• /
• pp.163-172
• /
• 2012

A driver assistance system is critical to improve a convenience and stability of vehicle driving. Several systems have been already commercialized such as adaptive cruise control system and forward collision warning system. Efficient vehicle detection is very important to improve such driver assistance systems. Most existing vehicle detection systems are based on a radar system, which measures distance between a host and leading (or oncoming) vehicles under various weather conditions. However, it requires high deployment cost and complexity overload when there are many vehicles. A camera based vehicle detection technique is also good alternative method because of low cost and simple implementation. In general, night time vehicle detection is more complicated than day time vehicle detection, because it is much more difficult to distinguish the vehicle's features such as outline and color under the dim environment. This paper proposes a method to detect vehicles at night time using analysis of a captured color space with reduction of reflection and other light sources in images. Four colors spaces, namely RGB, YCbCr, normalized RGB and Ruta-RGB, are compared each other and evaluated. A suboptimal threshold value is determined by Otsu algorithm and applied to extract candidates of taillights of leading vehicles. Statistical features such as mean, variance, skewness, kurtosis, and entropy are extracted from the candidate regions and used as feature vector for SVM(Support Vector Machine) classifier. According to our simulation results, the proposed statistical feature based SVM provides relatively high performances of leading vehicle detection with various distances in variable nighttime environments.

• 한국게임학회 논문지
• /
• 제15권4호
• /
• pp.29-38
• /
• 2015

스텔스 게임 레벨 디자이너는 다양한 난이도의 흥미로운 게임환경(레벨)을 제작해야 한다. J. Temblay와 공동 연구자들은 이 과정의 자동화를 돕는 Unity-기반 레벨 디자인 툴을 개발했다. 이 툴은 디자이너가 지도에서 경비병의 경로, 속도, 감시 영역, 플레이어의 출발점과 도착점 등 여러 게임 요소들을 입력하면 플레이어가 취할 수 있는 가능한 경로들을 포함한 다양한 시뮬레이션 결과들을 보여준다. 이를 이용해 디자이너는 현재의 게임 요소들이 자신이 의도한 난이도 및 플레이어 경로를 만드는지 실시간으로 확인할 수 있고, 필요한 경우 이들을 조정할 수 있게 되었다. 여기서는 두 가지 면에서 이 툴의 개선점을 제시한다. 첫째, 디자이너가 몇 개의 지점을 입력하면 이 지점들을 포함하는 흥미로운 경비병의 감시 경로를 난이도별로 추천해주는 기능을 추가해서 레벨 디자인 툴로서의 편의성과 유용성을 높였다. 둘째, 기존의 충돌 체크 함수 및 RRT-기반 경로 탐색 함수를 새로운 충돌 체크 함수와 델로네 로드맵-기반 경로 탐색 함수로 대체하여 시뮬레이션 속도를 크게 향상시켰다.