• Journal of information and communication convergence engineering
• /
• v.6 no.3
• /
• pp.331-336
• /
• 2008

In this paper, we propose a real-time people tracking system with multiple CCD cameras for security inside the building. To achieve this goal, we present a method for 3D walking human tracking based on the IMPRESARIO framework incorporating cascaded classifiers into hypothesis evaluation. The efficiency of adaptive selection of cascaded classifiers has been also presented. The camera is mounted from the ceiling of the laboratory so that the image data of the passing people are fully overlapped. The implemented system recognizes people movement along various directions. To track people even when their images are partially overlapped, the proposed system estimates and tracks a bounding box enclosing each person in the tracking region. The approximated convex hull of each individual in the tracking area is obtained to provide more accurate tracking information. We have shown the improvement of reliability for likelihood calculation by using cascaded classifiers. Experimental results show that the proposed method can smoothly and effectively detect and track walking humans through environments such as dense forests.

• Fibers and Polymers
• /
• v.5 no.1
• /
• pp.12-18
• /
• 2004

A parametric body model generation system has been developed. Using various mathematic and geometric algorithms of this system, a three-dimensionally scanned human body can be converted into a resizable body model. Once a parametric body model is formed, its size and shape can be modified instantaneously by providing appropriate anthropometric data. To facilitate the subsequent pattern arrangement process for garment drape simulation, a bounding box generation algorithm has been developed in this study. Also the model can be converted into a set of parametric surfaces that it can also be used for three-dimensional garment pattern design system.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.11a
• /
• pp.228-230
• /
• 2000

본 연구에서는 시청각 위주의 VR 멀티미디어 환경에 후각자극을 제시함으로써 더욱 현장감 있는 상황을 느낄 수 있는 칩타입 향 발생장치를 개발하였다. 셀마다 향과 Heating Coil을 함유하고 있는 IC 타입의 향 Container, DC Motor와 IC Holder를 포함하는 향 Housing, 전체적인 제어를 담당하는 Hardware Controller와 후각정보가 Encoding된 멀티미디어로 구성된다. 멀티미디어 매체 제작시 각 Object에 대한 Bounding Box를 설정하여 해당 영역에서만 향이 발산되도록 하였고 향발생장치를 Virtual Driving Simulator에 적용하여 화면의 영상과 함께 해당 향이 잘 발산되어 더욱 현실감 있는 VR 멀티미디어를 구현하였다.

• Journal of the Optical Society of Korea
• /
• v.15 no.2
• /
• pp.152-154
• /
• 2011

We propose a novel method which detects convex and concave corners using radial projection. The sum of two neighbors' differences at the local maxima or minima of the radial projection is compared with the angle threshold for detecting corners. In addition, the use of oriented bounding box trees and partial circles makes it possible to detect the corners of complex shapes. The experimental results show that the proposed method can separately detect the convex and concave corners, and that this method is scale invariant.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.1
• /
• pp.85-92
• /
• 2020

Object detection plays a critical role in the field of computer vision, and various researches have rapidly increased along with applying convolutional neural network and its modified structures since 2012. There are representative object detection algorithms, which are convolutional neural networks and YOLO. This paper presents two representative algorithm series, based on CNN and YOLO which solves the problem of CNN bounding box. We compare the performance of algorithm series in terms of accuracy, speed and cost. Compared with the latest advanced solution, YOLO v3 achieves a good trade-off between speed and accuracy.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.11a
• /
• pp.100-103
• /
• 2015

본 논문에서는 실내에서 RGBD 영상을 이용하여 물체를 검출하는 방법을 제안한다. 특정 물체가 아닌 일반적인 여러 가지 물체에 대한 특징을 규정하기 어려우므로 본 논문에서는 영상 정보에 의존하기 보다 물체와 픽셀의 기하학적 구조에 기반하여 물체를 검출한다. 우선 컬러 정보를 이용하여 대략적인 영상 영역분할을 하고 이를 같은 레이블로 분류하여 물체와 배경의 후보를 얻는다. 대체로 실내 환경에서 바닥은 평면이라 가정할 수 있으므로 바닥의 평면 모델을 만들어서 물체 후보에서 이를 제외시킨다. 또한, 물체에 대한 간단한 가정을 통해 바닥 이외의 배경 역시 물체와 구분하여서 물체 후보들을 가려낸다. 최종적으로 3 차원 공간에서 가까이 위치하는 레이블을 하나로 통합하는 과정을 통해 최종적인 물체 영역을 검출하고 이를 bounding box 로 표시한다. 직접 촬영한 몇몇 실내 RGBD 영상에서 실험한 결과, 제안하는 방법이 기존 방법들에 비해 물체 검출 성능이 좋은 것을 확인하였다.

• Journal of the Semiconductor & Display Technology
• /
• v.10 no.3
• /
• pp.53-59
• /
• 2011

This paper proposes a new method of traffic signal detection and recognition in an RGB color model. The proposed method firstly processes RGB-filtering in order to detect traffic signal candidates. Secondly, it performs adaptive threshold processing and then analyzes connected components of the binary image. The connected component of a traffic signal has to be satisfied with both a bounding box rate and an area rate that are defined in this paper. The traffic signal recognition system is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiment results show that the proposed algorithms are quite successful.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.41 no.8
• /
• pp.922-931
• /
• 1992

This paper presents an efficient algorithm for converting the boundary representation of a polyhedron to its corresponding octree representation which is convenient for detecting intersection between objects. In order to determine the states of octants efficiently and quickly, our algorithm consists of three basic processes which use the bounding box, the infinite plane and the projection. In our conversion algorithm, the states of octants are determined by performing one of these three processes according to the intersecting pattern of an octant with a polyhedron, instead of by performing only a face-to-face intersection test repeatedly. In particular, states of 8 suboctants are determined completely by performing the process using only the infinite plane, when the given octant is intersected with only a patch of the polyhedron. Finally, by using a 3D display method and a volume ratio method, it is confirmed that the octree converted by out algorithm is accurate. It is also confirmed that the conversion time is reduced in our algorithm.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.11
• /
• pp.139-147
• /
• 1999

Rapid Prototyping has made a drastic change in all industries which needs to reduce the time for the development of new products. Orientation and packing in rapid prototyping is considered as the most important factors to maximize the utilization of space in the build chamber and reduce build time. However, the decision of these parameter is mainly dependant on the operators's experience. This paper presents the methodology to find the optimal build layout considering an orientation and packing of multiple parts in SLS processing. Each part is represented as a voxel structure to deal with the inefficiency in a bounding box approach. Test results show that the adapted BL algorithm with a genetic algorithm(GA) can be applicable to a real industry.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.5
• /
• pp.2327-2347
• /
• 2018

Human actions can be recognized from depth sequences. In the proposed algorithm, we initially construct depth, motion maps (DMM) by projecting each depth frame onto three orthogonal Cartesian planes and add the motion energy for each view. The body part of the action (BPoA) is calculated by using bounding box with an optimal window size based on maximum spatial and temporal changes for each DMM. Furthermore, feature vector is constructed by using BPoA for each human action view. In this paper, we employed an ensemble based learning approach called Rotation Forest to recognize different actions Experimental results show that proposed method has significantly outperforms the state-of-the-art methods on Microsoft Research (MSR) Action 3D and MSR DailyActivity3D dataset.