• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.23 no.11 s.170
• /
• pp.1929-1939
• /
• 1999

This paper presents a neural network approach, which was named PRONET, to 3D object recognition and pose calculation. 3D objects are represented using a set of centroidal profile patterns that describe the boundary of the 2D views taken from evenly distributed view points. PRONET consists of the training stage and the execution stage. In the training stage, a three-layer feed-forward neural network is trained with the centroidal profile patterns using an error back-propagation method. In the execution stage, by matching a centroidal profile pattern of the given image with the best fitting centroidal profile pattern using the neural network, the identity and approximate orientation of the real object, such as a workpiece in arbitrary pose, are obtained. In the matching procedure, line-to-line correspondence between image features and 3D CAD features are also obtained. An iterative model posing method then calculates the more exact pose of the object based on initial orientation and correspondence.

• Investigative Magnetic Resonance Imaging
• /
• v.9 no.1
• /
• pp.24-29
• /
• 2005

Purpose : Instead of conventional two-dimensional (2-D) visual stimuli, three-dimensional (3-D) visual stimuli with stereoscopic vision were employed for the study of functional Magnetic Resonance Imaging (f-MRI). In this paper f-MRI with 3-D visual stimuli is investigated in comparison with f-MRI with 2-D visual stimuli. Materials and Methods : The anaglyph which generates stereoscopic vision by viewing color coded images with red-blue glasses is used for 3-D visual stimuli. Two-dimensional visual stimuli are also used for comparison. For healthy volunteers, f-MRI experiments were performed with 2-D and 3-D visual stimuli at 3.0 Tesla MRI system. Results : Occipital lobes were activated by the 3-D visual stimuli similarly as in the f-MRI with the conventional 2-D visual stimuli. The activated regions by the 3-D visual stimuli were, however, larger than those by the 2-D visual stimuli by $18\%$. Conclusion : Stereoscopic vision is the basis of the three-dimensional human perception. In this paper 3-D visual stimuli were applied using the anaglyph. Functional MRI was performed with 2-D and 3-D visual stimuli at 3.0 Tesla whole body MRI system. The occipital lobes activated by the 3-D visual stimuli appeared larger than those by the 2-D visual stimuli by about $18\%$. This is due to the more complex character of the 3-D human vision compared to 2-D vision. The f-MRI with 3-D visual stimuli may be useful in various fields using 3-D human vision such as virtual reality, 3-D display, and 3-D multimedia contents.

• CDE review
• /
• v.3 no.3
• /
• pp.57-60
• /
• 1997

기계 부품을 설계함에 있어 솔리드 모델링 시스템의 사용을 골격으로 하는 CAD 시스템의 사용은 삼차원 모델링된 단일 물체에 대한 물성치(mass property)의 계산, FEM 해석을 위한 유한요소의 자동생성, 곡면에 대한 NC 공구경로(NC tool path)의 자동계산, 부품의 생산을 위한 가공 정보의 도출 등의 분야에 많은 도움을 주어 설계와 생산, 관리의 전 분야에 혁신적 효율화를 도모해주었다. 한편 이렇게 설계된 단품들은 대개의 경우 조립되어 조립체를 이루게 되고, 그 상태로 혹은 부품간에 상대운동을 하면서 원하는 기능을 구현하게 된다. 단품에 대해서처럼 이 과정에서도 CAD 시스템은 조립체의 삼차원 형상을 인식하고 필요한 정보를 제공해줌으로써 설계자에게 유용한 도구로 사용될 수 있는데 이를 조립체 모델링 시스템(Assembly Modeling System)이라 부르며, 현재에는 대부분의 솔리드 모델링 시스템에 그 기능이 채택되어 있다. 조립체 모델링에 관한 연구동향을 비교적 잘 정리한 문헌으로는 Turner와 Libardi의 것을 들 수 있다. 여기서는 이러한 조립체 모델링 시스템의 연구분야와 동향에 대해 또 나름으로의 시각으로 정리하였다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.10a
• /
• pp.500-503
• /
• 1997

In this paper, a method for recognizing 3-D objects using the 3-D Hough transform and the robust stereo vision is studied. A 3-D object is recognized through two steps; modeling step and matching step. In modeling step, features of the object are extracted by analyzing the IGES file. In matching step, the values of the sensed image are compared with those of the IGES file which is assumed to location and orientation in the 3-D Hough transform domain. Since we use the 3-D Hough transform domain of the input image directly, the sensitivity to the noise and the high computational complexity could be significantly allcv~ated. Also, the cost efficiency is improved using the robust stereo vision for obtaining depth map image which is needed for 3-D Hough transform. In order lo verify the proposed method, real telephone model is recognized. Thc results of the location and orientation of the model are presented.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.131-132
• /
• 2022

We generate classifications and scenarios for intrusions based on 3D LiDAR Data. Research was conducted to analyze and diversify various actual intrusion cases to establish a system that can recognize objects and identify and guard data on intrusion. By generating and simulating basic scenarios for cars, people, animals, natural objects and etc, we create a classification scheme necessary to build and evaluate systems for intrusion. Based on the finally constructed scenario, we add variables for vehicles and surrounding objects to diversify scenarios, and lay the foundation for building accurate and automated alerting systems for future intrusions.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.586-588
• /
• 1998

영상처리의 결과로 얻어지는 에지나 선분과 같은 영상특성들은 그래픽의 기본 요소인 프리미티브들로 표현될 수 있다. 영상처리 결과를 그래픽 프리미티브로 표현하게 되면 보다 효율적으로 visualization할 수 있고 그래픽 환경의 편집기능을 이용하여 새로운 그래픽스를 생성할 수 있다. 반대로 그래픽 기술을 이용하여 생성된 영상은 패턴인식이나 Model Based 삼차원 물체인식 등에 사용될 수 있다. 이처럼 영상처리와 그래픽스는 서로 밀접한 관계를 가지고 있지만 이 두 분야를 지원하는 자료구조는 이를 반영하지 않고 있다. 영상처리를 위한 자료구조는 신속한 접근을 목표로 개발된 반면 그래픽스를 위한 자료구조는 공간절약과 빠른 display를 목표로 설계되었다. 본 연구에서는 영상처리와 그래픽스를 동시에 효과적으로 지원할 수 있는 자료구조를 설계하고 구현한다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.9
• /
• pp.1171-1180
• /
• 1995

In this paper, we present a 3-D object recognition system in which the 3-D Hough transform domain is employed to represent the 3-D objects. In object modeling step, the features for recognition are extracted from the CAD models of objects to be recognized. Since the approach is based on the CAD models, the accuracy and flexibility are greatly improved. In matching stage, the sensed image is compared with the stored model, which is assumed to yield a distortion (location and orientation) in the 3-D Hough transform domain. The high dimensional (6-D) parameter space, which defines the distortion, is decomposed into the low dimensional space for an efficient recognition. At first we decompose the distortion parameter into the rotation parameter and the translation parameter, and the rotation parameter is further decomposed into the viewing direction and the rotational angle. Since we use the 3-D Hough transform domain of the input images directly, the sensitivity to the noise and the high computational complexity could be significantly alleviated. The results show that the proposed 3-D object recognition system provides a satisfactory performance on the real range images.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.657-664
• /
• 2003

Reliable tracking of moving humans is essential to motion estimation, video surveillance and human-computer interface. This paper presents a new approach to human motion tracking that combines appearance-based and model-based techniques. Monocular color video is processed at both pixel level and object level. At the pixel level, a Gaussian mixture model is used to train and classily individual pixel colors. At the object level, a 3D human body model projected on a 2D image plane is used to fit the image data. Our method does not use inverse kinematics due to the singularity problem. While many others use stochastic sampling for model-based motion tracking, our method is purely dependent on nonlinear programming. We convert the human motion tracking problem into a nonlinear programming problem. A cost function for parameter optimization is used to estimate the degree of the overlapping between the foreground input image silhouette and a projected 3D model body silhouette. The overlapping is computed using computational geometry by converting a set of pixels from the image domain to a polygon in the real projection plane domain. Our method is used to recognize various human motions. Motion tracking results from video sequences are very encouraging.

• Journal of The Korean Association of Information Education
• /
• v.3 no.1
• /
• pp.134-142
• /
• 1999

The demand for recognizing the color as well as the object shape is increasing to use the detailed information, because-the expense of color input/output devices become cheap. The research on the color correction should be researched for the exact color presentation and color reproduction of color input/output systems. In this paper, we researched on the color correction of color scanner. The characterization of color scanner is a two step process of gray-balancing and color transformation. The decoupling of the gray-balancing from the color transformation enables the portability of the scanner characterization. We used the least square methods for the line fitting and the Neural Network for the storage space and computation speed. The output of Neural Network is similar to the target value in three-dimensional tristimulus space. The proposed color correction method can be used for all scanners of a manufacturer's model because of the portability.