• 한국항행학회논문지
• /
• 제11권1호
• /
• pp.59-63
• /
• 2007

본 논문은 윤곽선이 불분명한 상황에서 체형의 윤곽선과 신체 내부의 그리드 패턴들을 추출하기 위한 이미지 분할 알고리즘을 서술한다. 이미지 분할 방법은 문턱 값을 이용한 이진화 기법을 사용한다. 복잡한 형상을 지닌 물체의 3차원 정보를 추출하기 위한 노이즈 제거 알고리즘은 $3{\times}3$ 하이브리드 고역통과 필터 방법을 제안한다. 본 하이브리드 고역통과 필터 알고리즘은 노이즈 제거 시간이 기존 방법에 대하여 훨씬 단축되기 때문에 3차원 체형, CAD 시스템, 공장자동화와 같은 복잡한 형상을 지닌 물체의 3차원 정보를 추출하는데 적용할 수 있다.

• 비파괴검사학회지
• /
• 제10권1호
• /
• pp.10-17
• /
• 1990

Recently, object recognition ultrasonic sensor is being used with automatization of industrial machine. Points which characterize the object can be deleted by measuring the propagation time of ultrasonic impulse and azimuth which gives its maximum amplitude, and from these points shape, position and orientation of the object are deduced. A new measuring method is adopted, where the distance to the object is calculated by sound reflection time which is measured from O-cross point of sound wave, and azimuth is measured by angle indicating maximum amplitude. The measuring accuracy of 1.0mm for distance and $0.5-2^{\circ}$ for azimuth have been accomplished. By rotational scanning of sensor the characteristic point of an object can be known and it gives the information of its shape, position and orientation. Experimental results showed that the object of some complicated shape can be recognized, which suggest its applicability to robot.

• 제어로봇시스템학회논문지
• /
• 제12권8호
• /
• pp.746-751
• /
• 2006

In this paper, we present tracking algorithm for the indoor moving object. We research passive method using a camera and image processing. It had been researched to use dynamic based estimators, such as Kalman Filter, Extended Kalman Filter and Particle Filter for tracking moving object. These algorithm have a good performance on real-time tracking, but they have a limit. If the shape of object is changed or object is located on complex background, they will fail to track them. This problem will need the complicated image processing algorithm. Finally, a large algorithm is made from integration of dynamic based estimator and image processing algorithm. For eliminating this inefficiency problem, image based estimator, Mean-shift Algorithm is suggested. This algorithm is implemented by color histogram. In other words, it decide coordinate of object's center from using probability density of histogram in image. Although shape is changed, this is not disturbed by complex background and can track object. This paper shows the results in real camera system, and decides 3D coordinate using the data from mean-shift algorithm and relationship of real frame and camera frame.

• 한국전산유체공학회:학술대회논문집
• /
• 한국전산유체공학회 1996년도 춘계 학술대회논문집
• /
• pp.111-117
• /
• 1996

The Delaunay triangulation technique was tested for complicated shapes of computational domain. While a simple geometry, both in topology and in geometry, was discretized well into triangular elements. a complex geometry often failed in triangularization. A complex geometry should be devided into smaller sub-domains whose shape is simple both topologically and geometrically. The present study developed the data structures not only for relationships among neibering elements but also for shape information, and coupled these into the Delaunay triangulation technique. This approach was able to enhance greatly the reliability of triangularization specially in complicated shapes of computational domains. The GUI (Graphic User Interface) and OOP (Object-Oriented Programming) were used in order to develop the user-friendly and efficient computer code.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2009년도 학술대회
• /
• pp.56-61
• /
• 2009

공간 스케치에서 그리고자 하는 모델의 종류에 따라 효율적인 입력장치가 다르게 정의될 수 있다. 범용적인 공간 스케치 시스템에서 다양한 형태의 완드 형태를 지원하여 그리고자 하는 모델 또는 모델의 특정 부분에 적합한 완드의 형태를 바꾸어 가며 사용함으로써 효율적인 공간 스케치를 수행할 수 있다. 모델을 스케치 하는 중에 완드의 형태를 변형하기 위하여 기존의 메뉴를 사용하지 않고, 완드의 자세 또는 경로를 조절함으로써 완드의 타입과 형태를 바꾸는 완드 스타일을 제안하였으며, 완드의 입력 데이터를 격자 기반의 드로잉 기법을 사용하여 공간 스케치 시스템에 적용하였다.

• 한국기계가공학회지
• /
• 제15권2호
• /
• pp.38-45
• /
• 2016

Since a 5-axis machine tool has two rotary axes, it offers numerous advantages, such as flexible accessibility, longer tool life, better surface finish, and more accuracy. Moreover, it can conduct whole machining by rotating the rotary feed axes while setting the fixture at once without re-fixing in contrast to conventional 3-axis machining. However, it is difficult to produce complicated products that have a hollow shape. In contrast, 3D printing can produce an object with a complicated hollow shape easily and rapidly. However, because of layer thickness and shrinkage, its surface finish and dimensional accuracy are not adequate. Therefore, this study proposes hybrid technology by integrating the advantages of these two manufacturing processes. 3D printing was used as the additive manufacturing rapidly in the whole body, and 5-axis machining was used as the subtractive manufacturing accurately in the joining and driving places. The reliability of the proposed technology was verified through a comparison with conventional technology in the aspects of processing time, surface roughness. and dimensional accuracy.

• 한국전산유체공학회지
• /
• 제2권2호
• /
• pp.97-103
• /
• 1997

A modified Delaunay triangulation technique is tested for complicated computational domain. While a simple geometry. both in topology and geometry, has been well discretized into triangular elements, a complex geometry having difficulty in triangulation had to be divided into small sub-domains of simpler shape. The present study presents a modified Delaunay triangulation method based on the data structure of geometric modeller. This approach greatly enhances the reliability of triangulation, especially in complicated computational domain. We have shown that efficiency of Delaunay triangulation can be much improved by using both the GUI (Graphic User Interface) and OOP (Object-Oriented Programming).

• 한국멀티미디어학회논문지
• /
• 제22권2호
• /
• pp.136-145
• /
• 2019

The crowded environment of a domestic pig farm is highly vulnerable to the spread of infectious diseases such as foot-and-mouth disease, and studies have been conducted to automatically analyze behavior of pigs in a crowded pig farm through a video surveillance system using a camera. Although it is required to correctly separate occluding pigs for tracking each individual pigs, extracting the boundaries of the occluding pigs fast and accurately is a challenging issue due to the complicated occlusion patterns such as X shape and T shape. In this study, we propose a fast and accurate method to separate occluding pigs not only by exploiting the characteristics (i.e., one of the fast deep learning-based object detectors) of You Only Look Once, YOLO, but also by overcoming the limitation (i.e., the bounding box-based object detector) of YOLO with the test-time data augmentation of rotation. Experimental results with two-pigs occlusion patterns show that the proposed method can provide better accuracy and processing speed than one of the state-of-the-art widely used deep learning-based segmentation techniques such as Mask R-CNN (i.e., the performance improvement over Mask R-CNN was about 11 times, in terms of the accuracy/processing speed performance metrics).

• Current Optics and Photonics
• /
• 제2권6호
• /
• pp.554-562
• /
• 2018

This study presents a color 3D scanner based on the laser structured-light imaging method that can simultaneously acquire 3D shape data and color of a target object using a single camera. The 3D data acquisition of the scanner is based on the structured-light imaging method, and the color data is obtained from a natural color image. Because both the laser image and the color image are acquired by the same camera, it is efficient to obtain the 3D data and the color data of a pixel by avoiding the complicated correspondence algorithm. In addition to the 3D data, the color data is helpful for enhancing the realism of an object model. The proposed scanner consists of two line lasers, a color camera, and a rotation table. The line lasers are deployed at either side of the camera to eliminate shadow areas of a target object. This study addresses the calibration methods for the parameters of the camera, the plane equations covered by the line lasers, and the center of the rotation table. Experimental results demonstrate the performance in terms of accurate color and 3D data acquisition in this study.

• 방송공학회논문지
• /
• 제25권3호
• /
• pp.362-373
• /
• 2020

최근 자율 주행 자동차와 지능형 CCTV에 대한 관심이 높아지면서 효율적인 객체 검출의 중요성은 필수적인 요소이다. 본 논문의 기반이 되는 DPM(Deformable Part Models)은 객체에 대한 변형 가능한 부분의 혼합을 사용하여 가변적인 객체를 나타낼 수 있는 대표적인 검출기로 다양한 분야에서 많이 연구 되고 있다. 객체 모델의 파트 모양과 구성을 잡아내는 기법으로 높은 검출 성능을 보여주지만 복잡한 알고리즘으로 인해 실제 어플리케이션에서 사용하기에는 한계가 있다. 이를 개선하기 위해 본 논문에서는 DPM에서 많은 연산을 필요로 하는 이미지 특징 피라미드(feature pyramid)를 구성하는 과정 대신, 특정 스케일에서 구해진 소수의 특징(feature) 맵에 적응적인 쌍선형(bilinear) 보간법을 이용하여 이미지 특징 피라미드를 재구성해 연산 속도를 줄이는 방법을 제안한다. 모의실험 결과, 제안된 방식의 DPM은 기존 DPM 방식 대비 검출 성능은 2.82%가 낮아졌지만 평균 연산 시간 10%를 향상시킴을 알 수 있었다.