• Journal of the Korea Society for Simulation
• /
• v.9 no.4
• /
• pp.41-50
• /
• 2000

We have many simulation constraints to meet as a modeled system becomes large and complex. Real-time simulations are the examples in that they are constrained by certain non-function constraints (e.g., timing constraints). In this paper, an enhanced hierarchical modeling methodology is proposed to efficiently deal with constraint-simulations. The proposed modeling method enhances hierarchical modeling methods to provide multi-resolution model. A simulation model is composed by determining the optimal level of abstraction that is guaranteed to meet the given simulation constraints. Four modeling activities are defined in the proposed method: 1) Perform the logical architectural design activity to produce a multi-resolution model, 2) Organize abstraction information of the multi-resolution model with AT (Abstraction Tree) structure, 3) Formulate the given constraints based on U (Integer Programming) approach and embrace the constraints to AT, and 4) Compose a model based on the determined level of abstraction with which the multi-resolution model can satisfy all given simulation constraints. By systematically handling simulation constraints while minimizing the modeler's interventions, we provide an efficient modeling environment for constraint-simulations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2328-2344
• /
• 2022

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.

• Journal of Information Processing Systems
• /
• v.16 no.4
• /
• pp.991-1000
• /
• 2020

We propose a content-based image retrieval system that uses a combination of completed local binary pattern (CLBP) and color autocorrelogram. CLBP features are extracted on a multi-resolution multi-direction filtered domain of value component. Color autocorrelogram features are extracted in two dimensions of hue and saturation components. Experiment results revealed that the proposed method yields a lot of improvement when compared with the methods that use partial features employed in the proposed method. It is also superior to the conventional CLBP, the color autocorrelogram using R, G, and B components, and the multichannel decoded local binary pattern which is one of the latest methods.

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.1
• /
• pp.19-27
• /
• 2014

Compressive sensing is an emerging sampling technique which enables sampling a signal at a much lower rate than the Nyquist rate. In this paper, we propose a novel framework based on Kronecker compressive sensing that provides multi-resolution image reconstruction capability. By exploiting the relationship of the sensing matrices between low and high resolution images, the proposed method can reconstruct both high and low resolution images from a single measurement vector. Furthermore, post-processing using BM3D improves its recovery performance. The experimental results showed that the proposed scheme provides significant gains over the conventional framework with respect to the objective and subjective qualities.

• ETRI Journal
• /
• v.45 no.1
• /
• pp.93-104
• /
• 2023

Coreference resolution is a task in discourse analysis that links several headwords used in any document object. We suggest pointer networks-based coreference resolution for Korean using multi-task learning (MTL) with an attention mechanism for a hierarchical structure. As Korean is a head-final language, the head can easily be found. Our model learns the distribution by referring to the same entity position and utilizes a pointer network to conduct coreference resolution depending on the input headword. As the input is a document, the input sequence is very long. Thus, the core idea is to learn the word- and sentence-level distributions in parallel with MTL, while using a shared representation to address the long sequence problem. The suggested technique is used to generate word representations for Korean based on contextual information using pre-trained language models for Korean. In the same experimental conditions, our model performed roughly 1.8% better on CoNLL F1 than previous research without hierarchical structure.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.5
• /
• pp.2366-2395
• /
• 2018

Multi-view super-resolution (MVSR) refers to the process of reconstructing a high-resolution (HR) image from a set of low-resolution (LR) images captured from different viewpoints typically by different cameras. These multi-view images are usually obtained by a camera array. In our previous work [1], we super-resolved multi-view LR images via image fusion (IF) and blind deblurring (BD). In this paper, we present a new MVSR method that jointly realizes IF and BD based on an integrated energy function optimization. First, we reformulate the MVSR problem into a multi-channel blind deblurring (MCBD) problem which is easier to be solved than the former. Then the depth map of the desired HR image is calculated. Finally, we solve the MCBD problem, in which the optimization problems with respect to the desired HR image and with respect to the unknown blur are efficiently addressed by the alternating direction method of multipliers (ADMM). Experiments on the Multi-view Image Database of the University of Tsukuba and images captured by our own camera array system demonstrate the effectiveness of the proposed method.

• Journal of KIISE
• /
• v.41 no.11
• /
• pp.992-1005
• /
• 2014

Coreference resolution finds all expressions that refer to the same entity in a document. Coreference resolution is important for information extraction, document classification, document summary, and question answering system. In this paper, we adapt Stanford's Multi-pass sieve system, the one of the best model of rule based coreference resolution to Korean. In this paper, all noun phrases are considered to mentions. Also, unlike Stanford's Multi-pass sieve system, the dependency parse tree is used for mention extraction, a Korean acronym list is built 'dynamically'. In addition, we propose a method that calculates weights by applying transitive properties of centers of the centering theory when refer Korean pronoun. The experiments show that our system obtains MUC 59.0%, $B_3$ 59.5%, Ceafe 63.5%, and CoNLL(Mean) 60.7%.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.263-265
• /
• 2003

The computation cost of image registration is affected by searching data size and space. This paper proposes an efficient image registration algorithm that uses multi-resolution wavelet decomposed image to reduce the data size search. The algorithm determines the correlation detection at low resolution on low-pass sub bands of wavelet and generate mask for higher resolution as part of a coarse to fine registration algorithm. The correlation matching is defined for coarse resolution similarity measurement, while mutual information (MI) is used at fine resolution. The results show that the new efficient mask-based algorithm improves computational efficiency and yields robust and consistent image registration results.

• Smart Structures and Systems
• /
• v.16 no.1
• /
• pp.47-65
• /
• 2015

A novel finite element (FE) model updating method based on multi-resolution analysis (MRA) is proposed. The true stiffness of the FE model is considered as the superposition of two pieces of stiffness information of different resolutions: the pre-defined stiffness information and updating stiffness information. While the resolution of former is solely decided by the meshing density of the FE model, the resolution of latter is decided by the limited information obtained from the experiment. The latter resolution is considerably lower than the former. Second generation wavelet is adopted to describe the updating stiffness information in the framework of MRA. This updating stiffness in MRA is realized at low level of resolution, therefore, needs less number of updating parameters. The efficiency of the optimization process is thus enhanced. The proposed method is suitable for the identification of multiple irregular cracks and performs well in capturing the global features of the structural damage. After the global features are identified, a refinement process proposed in the paper can be carried out to improve the performance of the MRA of the updating information. The effectiveness of the method is verified by numerical simulations of a box girder and the experiment of a three-span continues pre-stressed concrete bridge. It is shown that the proposed method corresponds well to the global features of the structural damage and is stable against the perturbation of modal parameters and small variations of the damage.

• Journal of Broadcast Engineering
• /
• v.2 no.1
• /
• pp.16-23
• /
• 1997

Among the main technologies to implement 3D TV succeeding HDTV, multi-viewpoint image display technique is rising as an important issue, which can display the viewpoint-dependent images corresponding to viewer's position. This paper presents a novel method that solves too much computational overload that is main drawback of previous methods. Using down sampling technique, multiresolution EPIs are made from multi-viewpoint image set and trace lines are detected in the lowest resolution EPI. The parameters of detected trace lines are transferred to higher resolution EPIs and revised by utilizing the information of the previous resolution EPI. This procedure is iterated until orignal resolution EPI. Using the proposed method, we have achieved the reduction of computational time and the robustness to noise in comparison to previous method.