• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.353-358
• /
• 2022

Due to the limited field of view of the pinhole camera, there is a lack of stability and accuracy in camera pose estimation applications such as visual SLAM. Nowadays, multiple-camera setups and large field of cameras are used to solve such issues. However, a multiple-camera system increases the computation complexity of the algorithm. Therefore, in multiple camera-assisted visual simultaneous localization and mapping (vSLAM) the multi-view tracking algorithm is proposed that can be used to balance the budget of the features in tracking and local mapping. The proposed algorithm is based on PanoSLAM architecture with a panoramic camera model. To avoid the scale issue 3D LiDAR is fused with omnidirectional camera setup. The depth is directly estimated from 3D LiDAR and the remaining features are triangulated from pose information. To validate the method, we collected a dataset from the outdoor environment and performed extensive experiments. The accuracy was measured by the absolute trajectory error which shows comparable robustness in various environments.

• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.960-966
• /
• 2009

A manifold is used to represent a relationship between high-dimensional data samples in low-dimensional space. In human pose estimation, it is created in low-dimensional space for processing image and 3D body configuration data. Manifold learning is to build a manifold. But it is vulnerable to silhouette variations. Such silhouette variations are occurred due to view-change, person-change, distance-change, and noises. Representing silhouette variations in a single manifold is impossible. In this paper, we focus a silhouette variation problem occurred by view-change. In previous view invariant pose estimation methods based on manifold learning, there were two ways. One is modeling manifolds for all view points. The other is to extract view factors from mapping functions. But these methods do not support one by one mapping for silhouettes and corresponding body configurations because of unsupervised learning. Modeling manifold and extracting view factors are very complex. So we propose a method based on triple manifolds. These are view manifold, pose manifold, and body configuration manifold. In order to build manifolds, we employ biased manifold learning. After building manifolds, we learn mapping functions among spaces (2D image space, pose manifold space, view manifold space, body configuration manifold space, 3D body configuration space). In our experiments, we could estimate various body poses from 24 view points.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.11B
• /
• pp.1303-1310
• /
• 2009

Glassless 3D display requires multiple images taken from different viewpoints to show a scene. The simplest way to get multi-view image is using multiple camera that as number of views are requires. To do that, synchronize between cameras or compute and transmit lots of data comes critical problem. Thus, generating such a large number of viewpoint images effectively is emerging as a key technique in 3D video technology. Image-based view synthesis is an algorithm for generating various virtual viewpoint images using a limited number of views and depth maps. In this paper, because the virtual view image can be express as a transformed image from real view with some depth condition, we propose an algorithm to compute multi-view synthesis from two reference view images and their own depth-map by stepwise duplex forward mapping. And also, because the geometrical relationship between real view and virtual view is repetitively, we apply our algorithm into OpenGL Shading Language which is a programmable Graphic Process Unit that allow parallel processing to improve computation time. We demonstrate the effectiveness of our algorithm for fast view synthesis through a variety of experiments with real data.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.48-56
• /
• 2023

The technology of Three-dimensional human posture estimation is used in sports, motion recognition, and special effects of video media. Among various methods for this, multi-view 3D human pose estimation is essential for precise estimation even in complex real-world environments. But Existing models for multi-view 3D human posture estimation have the disadvantage of high order of time complexity as they use 3D feature maps. This paper proposes a method to extend an existing monocular viewpoint multi-frame model based on Transformer with lower time complexity to 3D human posture estimation for multi-viewpoints. To expand to multi-viewpoints our proposed method first generates an 8-dimensional joint coordinate that connects 2-dimensional joint coordinates for 17 joints at 4-vieiwpoints acquired using the 2-dimensional human posture detector, CPN(Cascaded Pyramid Network). This paper then converts them into 17×32 data with patch embedding, and enters the data into a transformer model, finally. Consequently, the MLP(Multi-Layer Perceptron) block that outputs the 3D-human posture simultaneously updates the 3D human posture estimation for 4-viewpoints at every iteration. Compared to Zheng[5]'s method the number of model parameters of the proposed method was 48.9%, MPJPE(Mean Per Joint Position Error) was reduced by 20.6 mm (43.8%) and the average learning time per epoch was more than 20 times faster.

• Broadcasting and Media Magazine
• /
• v.15 no.1
• /
• pp.24-36
• /
• 2010

Nowadays, digital broadcasting providers have plan to extend their service area to 3D broadcasting without exchanging conventional system and equipments. The maintenance of backward compatibility to conventional 2D broadcasting system is very importance issue on digital broadcasting. To satisfy the requirement, highly-optimized MPEG-2 video encoder is essential for coding left-view and new video coding techniques having higher performance than MPEG-4 AVC/H.264 is needed for right-view since terrestrial broadcasting system has very limited and fixed bandwidth. In this paper, conventional video coding algorithms and new video coding algorithms are analyzed to present a capable solution for the best quality stereoscopic 3D broadcasting keeping backward compatibility within the bandwidth.

• The Journal of the Korean dental association
• /
• v.56 no.9
• /
• pp.479-490
• /
• 2018

3D printing technology supporting the specific patient medical services is actively being implemented in dentistry. The purpose of this study is to introduce the legal and institutional considerations to the medical practitioners in dentistry who must observe when they manufacture medical devices using 3D printers, and to provide a ways to activate and enhance their utilization in the domestic approval point of view for medical devices. Through the public data of government agencies and related organizations, the statutory system and compliance matters related to the manufacture of 3D printing medical devices have been examined and reviewed for the government's improvement efforts. Through the study, the government has been actively improving the system and making policy, but the active interest and participation of medical professionals and related workers are continually required to solve the problems which are scattered. 3D printing technology is expected to be more frequently utilized in the field of dentistry in near future. Therefore, it is essential to establish measures to improve the regulation through continuous cooperation with the related ministries with the long-term point of view enhancing smooth entry to the market for the medical devices by taking data from the continued research.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2002.08a
• /
• pp.883-886
• /
• 2002

A new exposure time scheduling scheme to implement the optimized photopolymer-based VHOE is proposed and using this method, the 8-view VHOE system is experimentally developed. The CGS dependence on the exposure energy is mathematically modeled using the fourth-order polynomial function and using this model optimized exposure-time schedule for recording the given multiple gratings in the photopolymer is calculated. In addition, basing on this suggested exposure-time schedule, 8-view VHOE is finally implemented and its performance is discussed.

• Journal of International Society for Simulation Surgery
• /
• v.1 no.2
• /
• pp.57-61
• /
• 2014

We present a robust 3D facial reconstruction method using a single image generated by face-specific super resolution technique. Based on the several consecutive frames with low resolution, we generate a single high resolution image and a three dimensional facial model based on it. To do this, we apply PME method to compute patch similarities for SR after two-phase warping according to facial attributes. Based on the SRI, we extract facial features automatically and reconstruct 3D facial model with basis which selected adaptively according to facial statistical data less than a few seconds. Thereby, we can provide the facial image of various points of view which cannot be given by a single point of view of a camera.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.288-289
• /
• 2022

In this paper, we propose a method of obtaining high density geometric information using multi-view structured light. Reconstruction error due to the difference in resolution between the projector and the camera occurs when reconstruction a 3D shape from a structured light system to a single projector. This shows that the error in the point cloud in 3D is also the same when reconstruction the shape of the object. So we propose a high density method using multiple projectors to solve such a reconstruction error.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.1
• /
• pp.1-9
• /
• 2007

In this paper, we propose a new 3D modeling and rendering system using multiple stereo cameras. When target objects are captured by cameras, each capturing PC segments the objects and estimates disparity fields, then they transmit the segmented masks, disparity fields, and color textures of objects to a 3D modeling server. The modeling server generates 3D models of the objects from the gathered masks and disparity fields. Finally, the server generates a video at the designated point of view with the 3D model and texture information from cameras.