• Journal of Gifted/Talented Education
• /
• v.5 no.1
• /
• pp.1-32
• /
• 1995

• Journal of Gifted/Talented Education
• /
• v.5 no.1
• /
• pp.33-36
• /
• 1995

• Journal of Gifted/Talented Education
• /
• v.5 no.1
• /
• pp.37-40
• /
• 1995

• Annual Conference of KIPS
• /
• 2003.11a
• /
• pp.325-328
• /
• 2003

본 논문에서는 주어진 손님 그래프 모델의 정점들과 간선들을 성능 파라미터들을 보다 우수하게 유지하면서 주인 그래프의 대응되는 정점들 및 경로들로 매핑시키는 "그래프 임베딩 문제"라고 불리는 그래프이론 문제를 다룬다. 높이가 N인 피라미드 모델을 손님 그래프로 하여 0$(4^{(k+1)}+2)/3{\times}2^{(N-k-1)}{\times}2^{(N-k-2)}$ 구조의 병렬컴퓨터 모델로 임베딩할 수 있는 새로운 매핑 함수를 제안하고 해당 함수 적용시 신장율이 $max\{(2^{(2k+1)}+4)/3,\;5{\cdot}2^{N-k-2}/8\}$로 개선됨을 증명함으로써 그 성능을 분석한다.

• Proceedings of the Korean Society for the Gifted Conference
• /
• 1995.04a
• /
• pp.1-32
• /
• 1995

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.1
• /
• pp.127-135
• /
• 2006

The image-based 3D modeling is the technique of generating a 3D graphic model from images acquired using cameras. It is being researched as an alternative technique for the expensive 3D scanner. In this paper, I propose the image-based 3D modeling system using calibrated camera. The proposed algorithm for rendering 3D model is consisted of three steps, camera calibration, 3D shape reconstruction and 3D surface generation step. In the camera calibration step, I estimate the camera matrix for the image aquisition camera. In the 3D shape reconstruction step, I calculate 3D volume data from silhouette using pyramidal volume intersection. In the 3D surface generation step, the reconstructed volume data is converted to 3D mesh surface. As shown the result, I generated relatively accurate 3D model.

• Journal of Digital Convergence
• /
• v.19 no.5
• /
• pp.307-313
• /
• 2021

In this paper, a lightweight network with fewer parameters compared to the existing object detection method is proposed. In the case of the currently used detection model, the network complexity has been greatly increased to improve accuracy. Therefore, the proposed network uses EfficientNet as a feature extraction network, and the subsequent layers are formed in a pyramid structure to utilize low-level detailed features and high-level semantic features. An attention process was applied between pyramid structures to suppress unnecessary noise for prediction. All computational processes of the network are replaced by depth-wise and point-wise convolutions to minimize the amount of computation. The proposed network was trained and evaluated using the PASCAL VOC dataset. The features fused through the experiment showed robust properties for various objects through a refinement process. Compared with the CNN-based detection model, detection accuracy is improved with a small amount of computation. It is considered necessary to adjust the anchor ratio according to the size of the object as a future study.

• Spatial Information Research
• /
• v.16 no.2
• /
• pp.193-206
• /
• 2008

If stereo images is used for Digital Elevation Model (DEM) generation, a DEM is generally made by matching left image against right image from stereo images. In stereo matching, tie-points are used as initial match candidate points. The number and distribution of tie-points influence the matching result. DEM made from matching result has errors such as holes, peaks, etc. These errors are usually interpolated by neighbored pixel values. In this paper, we propose the DEM generation method combined with automatic tie-points extraction using existing DEM, image pyramid, and interpolating new DEM using existing DEM for more reliable DEM. For test, we used IKONOS, QuickBird, SPOT5 stereo images and a DTED level 2 data. The test results show that the proposed method automatically makes reliable DEMs. For DEM validation, we compared heights of DEM by proposed method with height of existing DTED level 2 data. In comparison result, RMSE was under than 15 m.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.113-116
• /
• 2021

일반적으로 딥러닝 기반의 객체 검출(Object Detection)기법은 합성곱 신경망(Convolutional Neural Network, CNN)을 통해 입력된 영상의 특징(Feature)을 추출하여 이를 통해 객체 검출을 수행한다. 최근 자연어 처리 분야에서 획기적인 성능을 보인 트랜스포머(Transformer)가 영상 분류, 객체 검출과 같은 컴퓨터 비전 작업을 수행하는데 있어 경쟁력이 있음이 드러나고 있다. 본 논문에서는 YOLOv4-CSP의 CSP 블록을 개선한 one-stage 방식의 객체 검출 네트워크를 제안한다. 개선된 CSP 블록은 트랜스포머(Transformer)의 멀티 헤드 어텐션(Multi-Head Attention)과 CSP 형태의 공간 피라미드 풀링(Spatial Pyramid Pooling, SPP) 연산을 기반으로 네트워크의 Backbone과 Neck에서의 feature 학습을 돕는다. 본 실험은 MSCOCO test-dev2017 데이터 셋으로 평가하였으며 제안하는 네트워크는 YOLOv4-CSP의 경량화 모델인 YOLOv4s-mish에 대하여 평균 정밀도(Average Precision, AP)기준 2.7% 향상된 검출 정확도를 보인다.

• Elastomers and Composites
• /
• v.44 no.4
• /
• pp.378-383
• /
• 2009

In this study, the use of a condensed model is proposed for the simulation of forming of sandwich sheet with pyramid core. A corresponding finite element analysis for L-type bending is carried out to prove the accuracy and the effectiveness. In order to improve the accuracy of forming analysis, more precise modeling of core shape and consideration of work-hardening of previous core forming are carried out. Simulation results are compared with those of experiment. Deformation shape and post-buckling behavior by simulation are in good agreement with those of experiment for the considerable range of deformation. From the comparison of force-displacement curve, it is shown that the proposed model shows good prediction of post-buckling behavior.