• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(4)
• /
• pp.57-60
• /
• 2001

In this paper, we propose a new 3D object retrieval system using the shape information of 2D silhouette images. 2D images at different view points are derived from a 3D model and linked to the model. Shape feature of 2D image is extracted by a region-based descriptor. In the experiment, we compare the results of the proposed system with those of the system using curvature scale space(CSS) to show the efficiency of our system.

• 인터넷정보학회논문지
• /
• 제21권2호
• /
• pp.121-130
• /
• 2020

이 논문은 Generative Adversarial Network (GAN) 을 이용하여 증진된 이미지 데이터를 평가방식인 Inception Score (IS) 와 Frechet Inception Distance (FID) 계산시 inceptionV3 모델을 활용 하는 방식을 응용하여, 군 폐쇄망 네트워크 데이터를 이미지 형태로 평가하는 방법을 제안한다. 기존 존재하는 이미지 분류 모델들에 레이어를 추가하여 IncetptionV3 모델을 대체하고, 네트워크 데이터를 이미지로 변환 및 학습 하는 방법에 변화를 주어 다양한 시뮬레이션을 진행하였다. 실험 결과, atan을 이용해 8 * 8 이미지로 변환한 데이터에 대해 1개의 덴스 레이어 (Dense Layer)를 추가한 Densenet121를 학습시킨 모델이 네트워크 데이터셋 평가 모델로서 가장 적합하다는 결과를 도출하였다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1998년도 Proceedings of International Workshop on Advanced Image Technology
• /
• pp.147-153
• /
• 1998

This paper provides a method for video augmentation using image interpolation. In computer graphics or augmented reality, 3D information of a model object is necessary to generate 2D views of the model, which are then inserted into or overlayed on environmental views or real video frames. However, we do not require any three dimensional model but images of the model object at some locations to render views according to the motion of video camera which is calculated by an SFM algorithm using point matches under weak-perspective (scaled-orthographic) projection model. Thus, a linear view interpolation algorithm is applied rather than a 3D ray-tracing method to get a view of the model at different viewpoints from model views. In order to get novel views in a way that agrees with the camera motion the camera coordinate system is embedded into model coordinate system at initialization time on the basis of 3D information recovered from video images and model views, respectively. During the sequence, motion parameters from video frames are used to compute interpolation parameters, and rendered model views are overlayed on corresponding video frames. Experimental results for real video frames and model views are given. Finally, discussion on the limitations of the method and subjects for future research are provided.

• Journal of International Society for Simulation Surgery
• /
• 제2권1호
• /
• pp.13-16
• /
• 2015

Purpose We conducted a study on the reconstruction of the head's shape in 3D using the ToF depth sensor. A time-of-flight camera (ToF camera) is a range imaging camera system that resolves distance based on the known speed of light, measuring the time-of-flight of a light signal between the camera and the subject for each point of the image. The above method is the safest way of measuring the head shape of plagiocephaly patients in 3D. The texture, appearance and size of the head were reconstructed from the measured data and we used the SDF method for a precise reconstruction. Materials and Methods To generate a precise model, mesh was generated by using Marching cube and SDF. Results The ground truth was determined by measuring 10 people of experiment participants for 3 times repetitively and the created 3D model of the same part from this experiment was measured as well. Measurement of actual head circumference and the reconstructed model were made according to the layer 3 standard and measurement errors were also calculated. As a result, we were able to gain exact results with an average error of 0.9 cm, standard deviation of 0.9, min: 0.2 and max: 1.4. Conclusion The suggested method was able to complete the 3D model by minimizing errors. This model is very effective in terms of quantitative and objective evaluation. However, measurement range somewhat lacks 3D information for the manufacture of protective helmets, as measurements were made according to the layer 3 standard. As a result, measurement range will need to be widened to facilitate production of more precise and perfectively protective helmets by conducting scans on all head circumferences in the future.

• 스마트미디어저널
• /
• 제10권2호
• /
• pp.30-37
• /
• 2021

최근 웹툰이나 애니메이션을 3D 콘텐츠로 제작하는 사례가 증가하고 있다. 3D 콘텐츠 제작에서 모델링은 반드시 필요하지만 시간이 오래 걸리는 작업이다. 드로잉 기반 모델링을 사용하여 2D 카툰 원화에서 3D 모델을 생성하기 위해서는 라인 드로잉이 필요하다. 하지만 2D 카툰원화는 3D 모델의 기하학적 특성이 표현되지 않고 카툰원화의 제작 기법이 다양하여 일관성 있게 라인 드로잉 추출이 힘들다. 본 연구에서는 generative adversarial network (GAN) 모델을 사용하여 2D 카툰 원화에서 3D 모델의 기하학적 특성을 나타내는 라인 드로잉을 추출하는 방법을 제안하고 이를 실험한다.

• 대한원격탐사학회지
• /
• 제28권3호
• /
• pp.319-327
• /
• 2012

In this paper, we introduce a newly developed photogrammetric software for automatic generation of high quality geo-products and its performance assessment carried out using various satellite images. Our newly developed software provides the latest techniques of an optimized sensor modelling, ortho-image generation and automated Digital Elevation Model (DEM) generation for diverse remote sensing images. In particular, images from dual- and multi-sensor images can be integrated for 3D mapping. This can be a novel innovation toward a wider applicability of remote sensing data, since 3D mapping has been limited within only single-sensor so far. We used Kompsat-2, Ikonos, QuickBird, Spot-5 high resolution satellite images to test an accuracy of 3D points and ortho-image generated by the software. Outputs were assessed by comparing reliable reference data. From various sensor combinations 3D mapping were implemented and their accuracy was evaluated using independent check points. Model accuracy of 1~2 pixels or better was achieved regardless of sensor combination type. The high resolution ortho-image results are consistent with the reference map on a scale of 1:5,000 after being rectified by the software and an accuracy of 1~2 pixels could be achieved through quantitative assessment. The developed software offers efficient critical geo-processing modules of various remote sensing images and it is expected that the software can be widely used to meet the demand on the high-quality geo products.

• 한국컴퓨터그래픽스학회논문지
• /
• 제15권2호
• /
• pp.1-8
• /
• 2009

본 논문에서는 사용자가 입력한 사람의 신체 모델과 모델에 입혀질 옷의 두 이미지를 입력으로 하여 2D상에서 옷과 모델이 잘 어울리게 입혀지는 가상의 드레스 업(Dress up)시스템을 제안한다. 첫 번째 단계에서는 골격 구조의 조인트 정보를 이용하여 옷 이미지를 크게 변형시킨다. 다음으로 옷의 경계에 있는 점들을 샘플링 하여 모델의 경계에 있는 점과 매칭 시키고 그 점들을 이용해 최적화 단계를 거쳐 최종적인 피팅 결과를 도출해 낸다. 두 단계를 거쳐 피팅 된 옷의 경우 평면적으로 보이기 때문에 부자연스러운 결과를 보이게 되므로 자연스러운 렌더링 결과를 위해서 이를 3D로 재구성 (reconstruction)시킨다. 재구성된 3D구조로부터 쉐이딩 정보를 가져와 다시 2D상에서 렌더링을 함으로써 최종적인 결과를 도출하게 된다. 본 연구에서 제안된 시스템을 통해 2D 기반의 가상 옷 시뮬레이션 결과를 얻을 수 있게된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.929-944
• /
• 2019

Many critical applications require accurate real-time human action recognition. However, there are many hurdles associated with capturing and pre-processing image data, calculating features, and classification because they consume significant resources for both storage and computation. To circumvent these hurdles, this paper presents a recognition machine learning (ML) based system model which uses reduced data structure features by projecting real 3D skeleton modality on virtual 2D space. The MMU VAAC dataset is used to test the proposed ML model. The results show a high accuracy rate of 97.88% which is only slightly lower than the accuracy when using the original 3D modality-based features but with a 75% reduction ratio from using RGB modality. These results motivate implementing the proposed recognition model on an embedded system platform in the future.

• Journal of International Society for Simulation Surgery
• /
• 제1권2호
• /
• pp.83-86
• /
• 2014

Purpose This paper was purposed to suggest the method to produce the supportive helmet (head correction) for the infants who are suffering from plagiocephaly and to evaluate the level of transformation through 3D model. Method Either of CT or X-ray restored images has been used in making the supportive helmet (Head correction) in general, but these methods of measuring have problems in cost and safety. 3D surface measurement technology was suggested to solve such matters. Results It was to design the transformed model of the head within 0.7cm in average by scanning the surface of head and performing 3D restoration with marching cube and the changing rate of the head was compared in numerical data with 3D model. Conclusion The suggested methods displayed the better performance than the conventional method in respect of the speed and cost.

• 정보처리학회논문지A
• /
• 제13A권4호
• /
• pp.371-380
• /
• 2006

본 논문은 패션 디자인 분야에서 완성된 의상의 모델 사진을 활용해 다양한 원단(직물)을 직접 Draping함으로써 새로운 디자인을 창출할 수 있고 직접 샘플이나 시제품을 제작하지 않고도 시뮬레이션만으로 의상 작품을 확인 할 수 있다. 또한 모델과 원단 이미지에 대한 데이터베이스를 구축하여 실시간으로 Mapping 결과를 확인할 수 있는 시스템을 구현하였다. 그리고 여기에서 추출되는 시제품을 3D 모델에 입혀 시뮬레이션 할 수 있도록 하기 위한 과정으로 우선 여러 옷감 조각들을 이용하여 가상의 3D 인체 모델에 옷을 입히기 위한 의복 시뮬레이션 시스템을 제안한다. 제안된 시스템은 3D 인체 모델 파일과 2D 재단 패턴 파일을 읽어 들인 다음에 mass-spring model에 기반한 물리적 시뮬레이션에 의해 의복을 착용한 3D 모델을 생성한다. 본 논문의 시스템은 사실적인 시뮬레이션을 위하여 인체 모델을 구성하는 삼각형과 의복을 구성하는 삼각형 사이의 충돌을 검사하고 반응 처리를 수행하였다. 인체를 구성하는 삼각형의 수가 매우 많으므로, 이러한 충돌 검사 빛 반응 처리는 많은 시간을 필요로 한다. 이 문제를 해결하기 위하여, 본 논문에서는 Octree 공간 분할 기법을 이용하여 충돌 검사 및 반응 처리 수를 줄이는 방법을 이용하여 사실적인 영상을 생성할 수 있었고, 수초 이내에 가상 인체 모델에 의복을 입힐 수 있었다.