• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1445-1456
• /
• 2018

Environment perception and three-dimensional (3D) reconstruction tasks are used to provide unmanned ground vehicle (UGV) with driving awareness interfaces. The speed of obstacle segmentation and surrounding terrain reconstruction crucially influences decision making in UGVs. To increase the processing speed of environment information analysis, we develop a CPU-GPU hybrid system of automatic environment perception and 3D terrain reconstruction based on the integration of multiple sensors. The system consists of three functional modules, namely, multi-sensor data collection and pre-processing, environment perception, and 3D reconstruction. To integrate individual datasets collected from different sensors, the pre-processing function registers the sensed LiDAR (light detection and ranging) point clouds, video sequences, and motion information into a global terrain model after filtering redundant and noise data according to the redundancy removal principle. In the environment perception module, the registered discrete points are clustered into ground surface and individual objects by using a ground segmentation method and a connected component labeling algorithm. The estimated ground surface and non-ground objects indicate the terrain to be traversed and obstacles in the environment, thus creating driving awareness. The 3D reconstruction module calibrates the projection matrix between the mounted LiDAR and cameras to map the local point clouds onto the captured video images. Texture meshes and color particle models are used to reconstruct the ground surface and objects of the 3D terrain model, respectively. To accelerate the proposed system, we apply the GPU parallel computation method to implement the applied computer graphics and image processing algorithms in parallel.

• 디지털콘텐츠학회 논문지
• /
• 제12권2호
• /
• pp.157-164
• /
• 2011

유방암중 관상피내암으로 진단 받은 환자를 대상으로 조영제 주입전, 후의 감산된 영상과 3차원 재구성된 영상을 정량적으로 비교 분석하여 재구성된 영상의 효과와 유용성을 고찰 해보고자 한다. 조직학적으로 관상피 내암으로 진단 받은 환자 20명을 대상으로 3.0T MR scanner를 이용하여 감산된 영상과 3차원 재구성한 영상을 획득하였다. 분석 결과 감산 영상과 재구성한 영상에서 신호대 잡음비는 병변, 유관조직, 지방조직에서 재구성한 영상에서 높은 신호대 잡음비를 보였으며 두 영상에서의 대조 도대 잡음비는 차이를 보이지 않았다.

• 대한전자공학회논문지SP
• /
• 제48권1호
• /
• pp.122-131
• /
• 2011

최근에 널리 사용되고 있는 단일 영상 기반의 3차원 얼굴 복원 방법인 변형 가능한 3차원 얼굴 형상 모델(3D morphable shape model)은 입력 영상으로부터 2차원 얼굴 특징점들을 정확하게 추출할 경우, 입력 얼굴과 유사한 3차원 얼굴 형상을 생성할 수 있다. 그러나 실시간 3차원 얼굴 복원 시스템과 같이 사용자의 협조가 불가능한 경우에는 자동으로 얼굴 특징점들을 추출해야 하기 때문에, 특징점 추출 오류가 발생하여 정확한 3차원 얼굴 형상을 생성하기 어려운 문제가 있다. 이러한 문제를 해결하기 위해서, 본 논문에서는 특징점 추출 시 오추출 특징점과 정추출 특징점을 자동으로 분류하고, 정추출 특징점들만을 이용하여 3차원 얼굴을 복원하는 방법을 제안하였다. 실험결과에서는 특징점 자동 추출 오류를 고려하지 않은 기존 방법과 비교한 결과, 제안방법의 3차원 얼굴 복원 성능이 크게 향상되었음을 확인하였다.

• Journal of International Society for Simulation Surgery
• /
• 제1권2호
• /
• pp.99-102
• /
• 2014

The skull defect can be made after the trauma, oncologic problems or neurosurgery. The skull reconstruction has been the challenging issue in craniofacial fields for a long time. So far the skull reconstruction with autogenous bone would be the standard. Although the autogenous bone would be the ideal one for skull reconstruction, donor site morbidity would be the inevitable problem in many cases. Meanwhile various types of allogenic and alloplastic materials have been also used. However, skull reconstruction with many alloplastic material have produced no less complications including infection, exposure, and delayed wound healing. Because the 3D printing technique evolved so fast that 3D printed titanium implant were possible recently. The aim of this trial is to try to restore the original skull anatomy as possible using the 3D printed titanium implant, based on the mirrored three dimensional CT images based on the computer simulation. Preoperative computed tomography (CT) data were processed for the patient and a rapid prototyping (RP) model was produced. At the same time, the uninjured side was mirrored and superimposed onto the traumatized side, to create a mirror-image of the RP model. And we fabricated Titanium implant to reconstruct three-dimensional orbital structure in advance, using the 3D printer. This prefabricated Titanium-implant was then inserted onto the defected skull and fixed. Three dimensional printing technique of titanium material based on the computer simulation turned out to be very successful in this patient. Individualized approach for each patient could be an ideal way to manage the traumatic patients in near future.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.59-64
• /
• 2002

This paper presents a method for line segment extraction for 3-d building reconstruction. Building roofs are described as a set of planar polygonal patches, each of which is extracted by watershed-based image segmentation, line segment matching and coplanar grouping. Coplanar grouping and polygonal patch formation are performed per region by selecting 3-d line segments that are matched using epipolar geometry and flight information. The algorithm has been applied to high resolution aerial images and the results show accurate 3-d building reconstruction.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2012년도 춘계학술발표대회
• /
• pp.336-339
• /
• 2012

VTK is a free but professional development platform for images three-dimensional (3D) reconstruction and processing. It is powerful, open-source, and users can customize their own needs by self-development of great flexibility. To give the doctors more and detailed information by simulate dissection to the 3-D brain MRI image after reconstruction. A Visualization System (VS) is proposed to achieve 3D brain reconstruction and virtual dissection functions. Based on the free VTK visualization development platform and Visual Studio 2010 IDE development tools, through C++ language, using real people's MRI brain dataset, we realized the images 3D reconstruction and also its applications and extensions correspondingly. The display effect of the reconstructed 3D image is well and intuitive. With the related operations such as measurement, virtual dissection and so on, the good results we desired could be achieved.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 하계학술대회
• /
• pp.282-285
• /
• 2020

포인트 클라우드는 2D 이미지를 3D 로 복원하고 표현하는 방법으로써 많은 연구가 진행되고 있다. 하지만 포인트 클라우드로만 표현할 경우 포인트와 포인트 사이에 빈 공간이 존재하여 실제 3D 물체와 차이가 존재한다. Mesh Reconstruction 은 보다 실제 3D 물체처럼 보이기 위해 포인트와 포인트를 이어 mesh 를 생성하는 방법인데 생성된 mesh 의 quality 는 texturing 을 거친 최종 결과에 큰 영향을 끼친다. 기존에 존재하는 이미지를 기반으로 생성된 포인트 클라우드의 Mesh Reconstruction 방법은 노이즈에 어느 정도 강한 면을 보이지만 최종 결과에서 잘 이어진 mesh 를 생성하지 못하고 hole 이 존재하는 문제가 있다. 본 논문에선 노이즈에 강하면서 최종 결과에서 잘 이어진 mesh 를 만들 수 있도록 하는 Mesh Reconstruction 알고리즘을 제안한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권5호
• /
• pp.1690-1710
• /
• 2014

In this paper, we propose the rapid implementation of a 3-dimensional (3D) facial reconstruction from a single frontal face image and introduce a design for its application on a mobile device. The proposed system can effectively reconstruct human faces in 3D using an approach robust to lighting conditions, and a fast method based on a Canonical Correlation Analysis (CCA) algorithm to estimate the depth. The reconstruction system is built by first creating 3D facial mapping from a personal identity vector of a face image. This mapping is then applied to real-world images captured with a built-in camera on a mobile device to form the corresponding 3D depth information. Finally, the facial texture from the face image is extracted and added to the reconstruction results. Experiments with an Android phone show that the implementation of this system as an Android application performs well. The advantage of the proposed method is an easy 3D reconstruction of almost all facial images captured in the real world with a fast computation. This has been clearly demonstrated in the Android application, which requires only a short time to reconstruct the 3D depth map.

• Journal of International Society for Simulation Surgery
• /
• 제1권1호
• /
• pp.13-15
• /
• 2014

Nowadays, with advanced 3D printing techniques, the custom-made implant can be manufactured for the patient. Especially in skull reconstruction, it is difficult to design the implant due to complicated geometry. In large defect, an autograft is inappropriate to cover the defect due to donor morbidity. We present the process of manufacturing the 3D custom-made implant for skull reconstruction. There was one patient with skull defect repaired using custom-made 3D titanium implant in the plastic and reconstructive surgery department. The patient had defect of the left parieto-temporal area after craniectomy due to traumatic subdural hematoma. Custom-made 3D titanium implants were manufactured by Medyssey Co., Ltd. using 3D CT data, Mimics software and an EBM (Electron Beam Melting) machine. The engineer and surgeon reviewed several different designs and simulated a mock surgery on 3D skull model. During the operation, the custom-made implant was fit to the defect properly without dead space. The operative site healed without any specific complications. In skull reconstruction, autograft has been the treatment of choice. However, it is not always available and depends on the size of defect and donor morbidity. As 3D printing technique has been advanced, it is useful to manufacture custom-made implant for skull reconstruction.

• 방송공학회논문지
• /
• 제26권1호
• /
• pp.70-78
• /
• 2021

2차원 단일 영상에서 3차원 깊이 정보를 복원하는 기술은 다양한 한계 및 산업계에서 활용도가 매우 높은 기술임이 분명하다. 하지만 2차원 영상은 임의의 3차원 정보의 투사의 결과라는 점에서 내재적 깊이 모호성(Depth ambiguity)을 가지고 있고 이를 해결하는 문제는 매우 도전적이다. 이러한 한계점은 최근 인공지능 기술의 발달에 힘입어 2차원 영상과 3차원 깊이 정보간의 대응 관계를 학습하는 알고리즘의 발달로 극복되어 지고 있다. 이러한 3차원 깊이 정보 획득을 위한 인공지능 기술을 학습하기 위해서는 대응 관계를 나타내는 대규모의 학습데이터의 필요성이 절대적인데, 이러한 데이터는 취득 및 가공 과정에서 상당한 노동력을 필요로 하기에 제한적으로 구축이 가능하다. 따라서 최근의 기술 발전 동향은 대규모의 2차원 영상과 메타 데이터를 활용하여 3차원 깊이 정보를 예측하려는 약교사(Weakly-supervised) 인공지능 기술의 발전이 주를 이루고 있다. 본 고에서는 이러한 기술 발전 동향을 장면(Scene) 3차원 복원 기술과 객체(Object) 3차원 복원 기술로 나누어 요약하고 현재의 기술들의 한계점과 향후 나아갈 방향에 대해서 토의한다.