• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.653-663
• /
• 2009

In this paper, we propose a blind spots elimination system using three cameras. A wide-angle camera is attached on trunk for eliminating blind spots of a rear-view mirror and two cameras are attached on each side-view mirror for eliminating blind spots of vehicle's sides. In order to eliminate blind spots efficiently, we suggest a method to build a panoramic mosaic view with two side images and one wide-angle rear image. First, we obtain an undistorted image from a wide-angle camera of rear-view and calculate the focus-of-contraction (FOC) in undistorted images of rear-view while the car is moving straight forward. Second, we compute a homography among side-view images and an undistorted image of rear-view in flat road scenes. Next, we perform an image registration process after road and background region segmentation. Finally, we generate various views such as a cylinder panorama view, a top view and an information panoramic mosaic view.

• ETRI Journal
• /
• v.44 no.1
• /
• pp.51-61
• /
• 2022

In this paper, we introduced a novel voxel-wise UV parameterization and view-dependent texture synthesis for the immersive rendering of a truncated signed distance field (TSDF) scene model. The proposed UV parameterization delegates a precomputed UV map to each voxel using the UV map lookup table and consequently, enabling efficient and high-quality texture mapping without a complex process. By leveraging the convenient UV parameterization, our view-dependent texture synthesis method extracts a set of local texture maps for each voxel from the multiview color images and separates them into a single view-independent diffuse map and a set of weight coefficients for an orthogonal specular map basis. Furthermore, the view-dependent specular maps for an arbitrary view are estimated by combining the specular weights of each source view using the location of the arbitrary and source viewpoints to generate the view-dependent textures for arbitrary views. The experimental results demonstrate that the proposed method effectively synthesizes texture for an arbitrary view, thereby enabling the visualization of view-dependent effects, such as specularity and mirror reflection.

• Journal of Korea Multimedia Society
• /
• v.11 no.6
• /
• pp.860-868
• /
• 2008

Human detection techniques in outdoor scenes have been studied for a long time to watch suspicious movements or to keep someone from danger. However there are few methods of human detection in overhead or near-field view scenes, while lots of human detection methods in far-field view scenes have been developed. In this paper, a set of five features useful for human detection in overhead view scenes and another set of four useful features in near-field view scenes are suggested. Eight feature-candidates are first extracted by analyzing geometrically varying characteristics of moving objects in samples of video sequences. Then highly contributed features for each view scene to classifying human from other moving objects are selected among them by using a neural network learning technique. Through experiments with hundreds of moving objects, we found that each set of features is very useful for human detection and classification accuracy for overhead view and near-field view scenes was over 90%. The suggested sets of features can be used effectively in a PTZ camera based surveillance system where both the overhead and near-field view scenes appear.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.174-184
• /
• 2022

3D human pose estimation models can be classified into a multi-view model and a single-view model. In general, the multi-view model shows superior pose estimation performance compared to the single-view model. In the case of the single-view model, the improvement of the 3D pose estimation performance requires a large amount of training data. However, it is not easy to obtain annotations for training 3D pose estimation models. To address this problem, we propose a method to generate pseudo ground-truths of multi-view human pose data from a multi-view model and exploit the resultant pseudo ground-truths to train a single-view model. In addition, we propose a multi-view consistency loss function that considers the consistency of poses estimated from multi-view images, showing that the proposed loss helps the effective training of single-view models. Experiments using Human3.6M and MPI-INF-3DHP datasets show that the proposed method is effective for training single-view 3D human pose estimation models.

• Journal of KIISE:Databases
• /
• v.30 no.3
• /
• pp.252-272
• /
• 2003

The view mechanism provides users with appropriate portions of database through data filtering and integration. In the Web era where information proliferates, the view concept is also useful for XML, a future standard for data exchange on the Web. This paper proposes a method of implementing XML views called XML view indexing, whereby XML view xv is represented as an XML view index(XVI) which is a structure containing the identifiers of xv's underlying XML elements as well as the information on xv. Since XVI for xv stores just the identifiers of the XML elements but not the elements themselves, when a user requests to retrieve xv, its XVI should be materialized against xv's underlying XML documents. Also an efficient algorithm to incrementally maintain consistency of XVI given a update of xv's underlying XML documents is required. This paper proposes and implements data structures and algorithms for XML view indexing. The performance experiments on XML view indexing reveal that it outperforms view recomputation for repeated accesses to the view, and requires as much as about 30 times less storage space compared to XML view materialization though the latter takes less time for repeated accesses to the view due to no need of materialization.

• The KIPS Transactions:PartD
• /
• v.16D no.3
• /
• pp.381-394
• /
• 2009

As a technique to enhance reusability for the created artifacts in software modeling process, the model driven method such like MDA has been applied. Unfortunately, the hierarchical and systematic MDA based development technique using UML is poor yet. This causes the problem that the MDA modeling with high consistency and reusability based on MDA metamodel is not being realized. To solve this problem, this paper proposes a MDA (PIM/PSM) component modeling technique using 2+1 view integrated metamodel. At first, the meta-architecture view model which can represents development process view and MVC view is defined. Then, the hierarchical integrated metamodels per view are addressed separately for modeling process and MVC at metamodel level on the hierarchy of the defined meta-architecture view model. These metamodels are defined hierarchically by layering the modeling elements in PIM and PSM pattern for UML models and GUI models. Appling the proposed metamodel to an ISMS application system, it is shown as a component modeling case study based on MDA. Through this approach, we are able to perform a component model with consistency and hierarchy corresponding to development process and MVC way. Accordingly, this may improve more independence and reusability of model.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.6
• /
• pp.434-442
• /
• 2015

In this paper, we propose an integrated spatial and view scalable video codec based on high efficiency video coding (HEVC). The proposed video codec is developed based on similarity and uniqueness between the scalable extension and 3D multi-view extension of HEVC. To improve compression efficiency using the proposed scalable multi-view video codec, inter-layer and inter-view predictions are jointly employed by using high-level syntaxes that are defined to identify view and layer information. For the inter-view and inter-layer predictions, a decoded picture buffer (DPB) management algorithm is also proposed. The inter-view and inter-layer motion predictions are integrated into a consolidated prediction by harmonizing with the temporal motion prediction of HEVC. We found that the proposed scalable multi-view codec achieves bitrate reduction of 36.1%, 31.6% and 15.8% on the top of ${\times}2$, ${\times}1.5$ parallel scalable codec and parallel multi-view codec, respectively.

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.3
• /
• pp.118-127
• /
• 2014

This paper presents an efficient motion and disparity prediction method for multi-view video coding based on the high efficient video coding (HEVC) standard. The proposed method exploits inter-view candidates for effective prediction of the motion or disparity vector to be coded. The inter-view candidates include not only the motion vectors of adjacent views, but also global disparities across views. The motion vectors coded earlier in an adjacent view were found to be helpful in predicting the current motion vector to reduce the number of bits used in the motion vector information. In addition, the proposed disparity prediction using the global disparity method was found to be effective for interview predictions. A multi-view version based on HEVC was used to evaluate the proposed algorithm, and the proposed correspondence prediction method was implemented on a multi-view platform based on HEVC. The proposed algorithm yielded a coding gain of approximately 2.9% in a high efficiency configuration random access mode.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.1
• /
• pp.157-170
• /
• 2012

Recently, user-created video shows high increasing in production and consumption. Among these, videos records an identical subject in limited space with multi-view are coming out. Occurring main reason of this kind of video is popularization of portable camera and mobile web environment. Multi-view has studied in visually representation technique fields for point of view. Definition of multi-view has been expanded and applied to various contents authoring lately. To make user-created videos into multi-view contents can be a kind of suggestion as a user experience for new form of video consumption. In this paper, we show the possibility to make user-created videos into multi-view video content through analyzing multi-view video contents even there exist attribute differentiations. To understanding definition and attribution of multi-view classified and analyzed existing multi-view contents. To solve time axis arranging problem occurred in multi-view processing proposed audio matching method. Audio matching method organize feature extracting and comparing. To extract features is proposed MFCC that is most universally used. Comparing is proposed n by n. We proposed multi-view video contents that can consume arranged user-created video by user selection.

• KIEAE Journal
• /
• v.6 no.4
• /
• pp.3-10
• /
• 2006

To preserve scenic-view of Gwanak Mountain from the urban development, the viewshed component ratio and the scenic-view preference are investigated and analyzed by selecting view points at Nangokro. After 16 candidate view points are selected from the site, sight component ratio is measured through visual structure analysis and preference are measured by using the Likert scale. In addition, factor analysis, and regression analysis were conducted to examine the relationship between influencing factors and preference. As a result of the regression analysis of the 9 factors to influence the scenic-view preference, two factors such as degree of natural landscape and degree of arrangement around the site are chosen to influence the scenic-view preference. Through the preference factor analysis, two preference factors are selected as follows; 1) The factor of the landscape formation - Existence and nonexistence of the scenic-view conservation, degree of the landscape opening, and degree of natural landscape, degree of the landscape originality, and degree of the landscape sequence, degree of the landscape intimacy 2) The factor surrounding the landscape - Degree of arrangement around the site, degree of the landscape complexity, and atmosphere around the site.