• Journal of Korea Game Society
• /
• v.13 no.3
• /
• pp.85-94
• /
• 2013

In this paper, we propose a scheme to reduce the number of shadow tests conducted during rendering of ray tracing. The shadow test is a very important process in ray tracing to generate photo-realistic images. In the rendering phase, the ray tracer determines whether to cull the shadow test based on information calculated from a shadow test conducted on the kd-tree in the preprocessing phase. In conventional rendering process, the proposed method can be used with little modification. The proposed method is suitable for a static scene, in which the geometry and light source does not change in the same manner as it does in the conventional method. The validity of the proposed scheme is verified and its performance is evaluated during cycle-accurate simulation. Through experiment results, we found that we could reduce up to 17% of the shadow test.

• The Journal of the Korea Contents Association
• /
• v.6 no.1
• /
• pp.72-79
• /
• 2006

Recently, a MMORPG(Massively Multi-play Online Role Playing Game) has built distribute server by Seamless world. This paper proposes an efficient collision detection method. DLS is used to dynamically adjust spatial subdivisions in each the boundary regions of distribute server We use an index table to effectively utilize the relationships between in the nodes and can perform the collision detection efficiently by reconstructing nodes of the tree. Also, we maintain the information for the boundary region to efficiently detect the collections and adjust the boundary regions between distributed servers by using DLS. As the DLS uses pointers, the information for each server is not needed and the boundary regions between the distributed servers are efficiently searched. Using node index points, the construction table can be made to find between ray and neighborhood node, In addition, processes for Network traffic reduce because a copy of the boundary regions is not needed when a object moves with realtime.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.907-910
• /
• 2011

This paper proposes a character segmentation algorithm of steel plate images composed of adaptive binarization by the SCW (Sliding Concentric Windows) technique, the object labelling by CCA (Connected Component Analysis), and 2D projection method. The SCW technique carries out the grayscale-to-binary image conversion in consideration of local characteristics of images. The character decision algorithm followed by the labelling technique by CCA (Connected Component Analysis) determines the character area effectively reducing the noise effect. The 2D projection with horizontal and vertical directions produces a tight bounding box for a character based on the cross points. Experimental results indicate that the proposed algorithm segments the characters in steel plate images effectively. The proposed algorithm can be applied to the devices with limited resources due to its excellent performance and low complexity.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.8
• /
• pp.2017-2024
• /
• 1997

The main focus of this paper is the recognition of printed Hangul documents in terms of typeface, character size and character slope for IICS(Intelligent Image Communication System). The fixed-size blocks extracted from documents are analyzed in frequency domain for the typeface classification. The vertical pixel counts and projection profile of bounding box are used for the character size classification and the character slope classification, respectively. The MLP with variable hidden nodes and error back-propagation algorithm is used as typeface classifier, and Mahalanobis distance is used to classify the character size and slope. The experimental results demonstrated the usefulness of proposed system with the mean rate of 95.19% in typeface classification. 97.34% in character size classification, and 89.09% in character slope classification.

• Journal of Korea Multimedia Society
• /
• v.22 no.10
• /
• pp.1168-1177
• /
• 2019

In order to diagnose and prevent Alzheimer's Disease (AD), it is becoming increasingly important to develop a CAD(Computer-aided Diagnosis) system for AD diagnosis, which provides effective treatment for patients by analyzing 3D MRI images. It is essential to apply powerful deep learning algorithms in order to automatically classify stages of Alzheimer's Disease and to develop a Alzheimer's Disease support diagnosis system that has the function of detecting hippocampus and CSF(Cerebrospinal fluid) which are important biomarkers in diagnosis of Alzheimer's Disease. In this paper, for AD diagnosis, we classify a given MRI data into three categories of AD, mild cognitive impairment, and normal control according by applying 3D brain MRI image to the Faster R-CNN model and detect hippocampus and CSF in MRI image. To do this, we use the 2D MRI slice images extracted from the 3D MRI data of the Faster R-CNN, and perform the widely used majority voting algorithm on the resulting bounding box labels for classification. To verify the proposed method, we used the public ADNI data set, which is the standard brain MRI database. Experimental results show that the proposed method achieves impressive classification performance compared with other state-of-the-art methods.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.349-358
• /
• 2021

Recently, a method of finding the attention area or localization area for an object of an image using CAM (Class Activation Map)[1] has been variously carried out as a study of WSOL (Weakly Supervised Object Localization). The attention area extraction from the object heat map using CAM has a disadvantage in that it cannot find the entire area of the object by focusing mainly on the part where the features are most concentrated in the object. To improve this, using CAM and Selective Search[6] together, we first expand the attention area in the heat map, and a Gaussian smoothing is applied to the extended area to generate retraining data. Finally we train the data to expand the attention area of the objects. The proposed method requires retraining only once, and the search time to find an localization area is greatly reduced since the selective search is not needed in this stage. Through the experiment, the attention area was expanded from the existing CAM heat maps, and in the calculation of IOU (Intersection of Union) with the ground truth for the bounding box of the expanded attention area, about 58% was improved compared to the existing CAM.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.9
• /
• pp.1146-1151
• /
• 2019

Histogram H is an x-monotone rectilinear polygon with a horizontal edge, called by a base, connecting the leftmost vertical edge and the rightmost vertical edge. Here the rectilinear polygon is a polygon with only horizontal and vertical edges and the x- monotone polygon P is a polygon in which every line orthogonal to the x-axis intersects P at most twice. Walking counterclockwise on the boundary of a histogram H yields a sequence of left turns and right turns at its vertices. Conversely, a given sequence of the turns at the vertices can be realized by a histogram. In this paper, we consider the problem of finding a histogram to realize a given turn sequence. Particularly, we will find the histograms to minimize its area and its bounding box. It will be shown that both of the problems can be solved by linear time algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.1
• /
• pp.74-89
• /
• 2021

For higher-level requirements of urban planning and management and the recent development of "digital earth" and "digital city", it is urgent to establish protocols for the construction of three-dimensional digital city models. However, some problems still exist in the digital technology of the three-dimensional city model, such as insufficient precision of the three-dimensional model, not optimizing the scene and not considering the constraints of building codes. In view of those points, a method to interactively simulate a virtual city scene based on building codes is proposed in this paper. Firstly, some constraint functions are set up to restrict the models to adhere to the building codes, and an improved directional bounding box technique is utilized to solve the problem that geometric objects may intersect in a virtual city scene. The three-dimensional model invocation strategy is designed to convert two-dimensional layouts to a three-dimensional urban scene. A Leap Motion hardware device is used to interactively place the 3D models in a virtual scene. Finally, the design and construction of the three-dimensional scene are completed by using Unity3D. The experiment shows that this method can simulate urban virtual scenes that strictly adhere to building codes in a virtual scene of the city environment, but also provide information and decision-making functions for urban planning and management.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.11
• /
• pp.1357-1363
• /
• 2019

In this paper, we compares the performance of the gredient descent optimizers of the Faster Region-based Convolutional Neural Network (R-CNN) model for the chromosome object detection in digital images composed of human metaphase chromosomes. In faster R-CNN, the gradient descent optimizer is used to minimize the objective function of the region proposal network (RPN) module and the classification score and bounding box regression blocks. The gradient descent optimizer. Through performance comparisons among these four gradient descent optimizers in our experiments, we found that the Adamax optimizer could achieve the mean average precision (mAP) of about 52% when considering faster R-CNN with a base network, VGG16. In case of faster R-CNN with a base network, ResNet50, the Adadelta optimizer could achieve the mAP of about 58%.

• Land and Housing Review
• /
• v.14 no.1
• /
• pp.123-134
• /
• 2023

The BIM (Building Information Modeling) model created in the design stage can be used for prior review and schedule management for the construction stage. However, in the case of actual BIM application cases, additional work is required, such as creating a new model suitable for the construction stage, rather than using the 3D model in the design stage, due to the difference in the purpose of use between the design stage and the construction stage. Therefore, in this study, a division function of BIM model is proposed as a method of recycling it in the construction stage without a remodeling process. In addition, the application to the actual BIM model and the 4D CAD system linkage of the divided object and the comparison with the existing division method are used to verify the usability.