• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.264-272
• /
• 2019

In this paper, we propose a 3D human body reconstruction and refinement method from the frames extracted from a video to obtain natural and smooth motion in temporal domain. Individual frames extracted from the video are fed into convolutional neural network to estimate the location of the joint and the silhouette of the human body. This is done by projecting the parameter-based 3D deformable model to 2D image and by estimating the value of the optimal parameters. If the reconstruction process for each frame is performed independently, temporal consistency of human pose and shape cannot be guaranteed, yielding an inaccurate result. To alleviate this problem, the proposed method analyzes and interpolates the principal component parameters of the 3D morphable model reconstructed from each individual frame. Experimental result shows that the erroneous frames are corrected and refined by utilizing the relation between the previous and the next frames to obtain the improved 3D human reconstruction result.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.224-230
• /
• 2015

This manuscript presents a real-time solution for 3D human body reconstruction with multiple RGB-D cameras. The proposed system uses four consumer RGB/Depth (RGB-D) cameras, each located at approximately $90^{\circ}$ from the next camera around a freely moving human body. A single mesh is constructed from the captured point clouds by iteratively removing the estimated overlapping regions from the boundary. A cell-based mesh construction algorithm is developed, recovering the 3D shape from various conditions, considering the direction of the camera and the mesh boundary. The proposed algorithm also allows problematic holes and/or occluded regions to be recovered from another view. Finally, calibrated RGB data is merged with the constructed mesh so it can be viewed from an arbitrary direction. The proposed algorithm is implemented with general-purpose computation on graphics processing unit (GPGPU) for real-time processing owing to its suitability for parallel processing.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.5
• /
• pp.1-11
• /
• 2020

Image-based virtual try-on (VTON) is becoming popular for online apparel shopping, mainly because of not requiring 3D information for try-on clothes and target humans. However, existing 2D algorithms, even when utilizing advanced non-rigid deformation algorithms, cannot handle large spatial transformations for complex target human poses. In this study, we propose a 3D clothing reconstruction method using a 3D human body model. The resulting 3D models of try-on clothes can be more easily deformed when applied to rest posed standard human models. Then, the poses and shapes of 3D clothing models can be transferred to the target human models estimated from 2D images. Finally, the deformed clothing models can be rendered and blended with target human representations. Experimental results with the VITON dataset used in the previous works show that the shapes of reconstructed clothing are significantly more natural, compared to the 2D image-based deformation results when human poses and shapes are estimated accurately.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2009.11a
• /
• pp.99-102
• /
• 2009

본 연구에서는 실제 기증받은 시체를 이용하여 인체의 각 구조물을 실제 모습 그대로 3D 이미지화하는 과정에 대해 알아보았다. 인체의 구조물을 3D 로 이미지화하는 과정은 다음과 같다. 먼저 시체를 0.2mm 간격으로 절단하여 절단면의 사진을 찍은 후, 각 절단면의 사진에서 각각의 구조물을 구역화하여 색칠을 한 후, 구역화한 이미지에서 외곽선을 추출하여 벡터 이미지를 만든다. 이 외곽선을 1mm 간격으로 쌓아 올린 후 그 표면을 재구성하여 3D 이미지로 변환하는 과정으로 진행되었다. 3D 이미지의 제작은 가슴 부위에 한정하여 이루어졌다. 인체의 해부학적인 모형을 3D 이미지로 시각화함으로써 얻는 효과는 일반인을 대상으로 인체의 내부에 대한 시각적인 호기심을 충족시켜주고 의학 상식을 넓히는데 도움을 줄 수 있을 것 이다. 또한 의대생들을 비롯한 의학 전문가들에게는 생생한 해부학 강의용으로도 활용 가능하다. 향후 Haptic 시스템을 이용한 의료 실습 어플리케이션과 접목될 수도 있을것이고, fMRI 데이터를 비롯한 타 데이터와의 융합을 통해 시각화하여 서비스 할 수도 있다. 이처럼 인체의 3D 모형은 의료분야에서 광범위하게 활용될 수 있는 데이터로써 그 가치를 지닐 것이다.

• Journal of the Korean Society for Precision Engineering
• /
• v.26 no.12
• /
• pp.138-145
• /
• 2009

Custom medical treatment is being widely adapted to lots of medical applications. A technology for 3D modeling is strongly required to fabricate medical implants for individual patient. Needs on true 3D CAD data of a patient is strongly required for tissue engineering and human body simulations. Medical imaging devices show human inner section and 3D volume rendering images of human organs. CT or MRI is one of the popular imaging devices for that use. However, those image data is not sufficient to use for medical fabrication or simulation. This paper mainly deals how to generate 3D geometry data from those medical images. A new image processing technology is introduced to reconstruct 3D geometry of a human body vacancy from the medical images. Then a surface geometry data is reconstructed by using Marching cube algorithm. Resulting CAD data is a custom 3D geometry data of human vacancy. This paper introduces a novel 3D reconstruction process and shows some typical examples with implemented software.

• Journal of Biomedical Engineering Research
• /
• v.25 no.6
• /
• pp.537-543
• /
• 2004

In order to create three-dimensional model for human body, a method that reconstructs geometric models from contour lines on cross-section images is commonly used. We can get a set of contour lines by acquiring CT or MR images and segmenting anatomical structures. Previously proposed method divides entire contour line into simply matched regions and clefts. Since long processing time is required for reconstructing cleft regions, its performance might be degraded when manipulating complex data such as cross-sections for human body. In this paper, we propose a fast reconstruction method. It generates a triangle strip with single tiling operation for simple region that does not contain branch structures. If there exist branches in contour lines, it partitions the contour line into several sub-contours by considering the number of vertices and their spatial distribution. We implemented an automatic surface reconstruction system by using our method which reconstructs three-dimensional models for anatomical structures.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.8
• /
• pp.164-170
• /
• 2004

The skin movement artifacts are referred to as the relative motion of skin with respect to the motion of underlying bones. This is of great importance in joint biomechanics or internal kinematics of human body. This paper describes a novel experiment that measures the skin movement of a hand based on MR(magnetic resonance) images in conjunction with surface modeling techniques. The proposed approach consists of 3 phases: (1) MR scanning of a hand with surface makers, (2) 3D reconstruction from the MR images, and (3) registration of the 3D models. The MR images of the hand are captured by 3 different postures. And the surface makers which are attached to the skin are employed to trace the skin motion. After reconstruction of 3D models from the scanned MR images, the global registration is applied to the 3D models based on the particular bone shape of different postures. The results of registration are then used to trace the skin movement by measuring the positions of the surface markers.

• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.5
• /
• pp.17-25
• /
• 2019

In this paper, we introduce the technology to convert a single human image into a fashion show animation video clip. The technology can help the customers confirm the dynamic fitting result when combined with the virtual try on technique as well as the interesting experience to a normal person of being a fashion model. We developed an extended technique of full human 2D to 3D inverse modeling based on SMPLify human body inverse modeling technique, and a rigged model animation method. The 3D shape deformation of the full human from the body model was performed by 2 part deformation in the image domain and reconstruction using the estimated depth information. The quality of resultant animation videos are made to be publically available for evaluation. We consider it is a promising approach for commercial application when supplemented with the post - processing technology such as image segmentation technique, mapping technique and restoration technique of obscured area.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.4
• /
• pp.40-50
• /
• 2019

In recent years, it is important to visualize an accurate human body model for the low-end system in the medical imaging field where augmented reality technology and virtual reality technology are used. Decreasing the geometry of a model causes a difference from the original shape and considers the difference as an error. So, the error should be minimized while reducing geometry. In this study, the organ areas of a human body in the tomographic images such as CT or MRI is segmented and 3D geometric model is generated, thereby implementing the reconstruction method of multiple resolution level-of-detail model. In the experiment, a virtual reality platform was constructed to verify the shape of the reconstructed model, targeting the spine area. The 3D human body model and patient information can be verified using the virtual reality platform.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.15 no.1
• /
• pp.58-64
• /
• 2011

Objective: The 3-dimensional reconstruction method with resolution recovery modeling has advantages of high spatial resolution and contrast because of its precise modeling of spatial blurring according to the distance from detector plane. The aim of this study was to evaluate one of the resolution recovery reconstruction methods (Astonish, Philips Medical), compare it to other iterative reconstructions, and verify its clinical usefulness. Materials and Methods: NEMA IEC PET body phantom and Flanges Jaszczak ECT phantom (Data Spectrum Corp., USA) studies were performed using Skylight SPECT (Philips) system under four different conditions; short or long (2 times of short) radius, and half or full (40 kcts/frame) acquisition counts. Astonish reconstruction method was compared with two other iterative reconstructions; MLEM and 3D-OSEM which vendor supplied. For quantitative analysis, the contrast ratios obtained from IEC phantom test were compared. Reconstruction parameters were determined by optimization study using graph of contrast ratio versus background variability. The qualitative comparison was performed with Jaszczak ECT phantom and human myocardial data. Results: The overall contrast ratio was higher with Astonish than the others. For the largest hot sphere of 37 mm diameter, Astonish showed about 27.1% and 17.4% higher contrast ratio than MLEM and 3D-OSEM, in short radius study. For long radius, Astonish showed about 40.5% and 32.6% higher contrast ratio than MLEM and 3D-OSEM. The effect of acquired counts was insignificant. In the qualitative studies with Jaszczak phantom and human myocardial data, Astonish showed the best image quality. Conclusion: In this study, we have found out that Astonish can provide more reliable clinical results by better image quality compared to other iterative reconstruction methods. Although further clinical studies are required, Astonish would be used in clinics with confidence for enhancement of images.