• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.1
• /
• pp.9-16
• /
• 2002

This paper proposes a new 3D modeling technique using disparity-motion relationship and feature points. To generate the 3D model from real scene, generally, we need to compute depth of model vertices from the dense correspondence map over whole images. It takes much time and is also very difficult to get accurate depth. To improve such problems, in this paper, we only need to find the correspondence of some feature points to generate a 3D model of object without dense correspondence map. The proposed method consists of three parts, which are the extraction of object, the extraction of feature points, and the hierarchical 3D modeling using classified feature points. It has characteristics of low complexity and is effective to synthesize images with virtual view and to express the smoothness of Plain regions and the sharpness of edges.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.1
• /
• pp.93-114
• /
• 2023

Information extraction can facilitate the intensive analysis of documents by providing semantic triples which consist of named entities and their relations recognized in the texts. However, most of the research so far has been carried out separately for named entity recognition and relation extraction as individual studies, and as a result, the effective performance evaluation of the entire information extraction systems was not performed properly. This paper introduces two models of end-to-end information extraction that can extract various entity names in clinical records and their relationships in the form of semantic triples, namely pipeline and joint models and compares their performances in depth. The pipeline model consists of an entity recognition sub-system based on bidirectional GRU-CRFs and a relation extraction module using multiple encoding scheme, whereas the joint model was implemented with a single bidirectional GRU-CRFs equipped with multi-head labeling method. In the experiments using i2b2/VA 2010, the performance of the pipeline model was 5.5% (F-measure) higher. In addition, through a comparative experiment with existing state-of-the-art systems using large-scale neural language models and manually constructed features, the objective performance level of the end-to-end models implemented in this paper could be identified properly.

• 한국방재학회:학술대회논문집
• /
• 2007.02a
• /
• pp.203-206
• /
• 2007

In urban flood model, the features like roads, buildings, and river's banks have great effect on flow dynamics and flood propagation and it must be accounted for model set-up. Two-dimensional hydraulic models in high-density building areas are at the forefront of current research into flood inundation mechanisms, but they are however constrained by inadequate parameters of topography and friction due to insufficient and inaccurate data. This paper describes the development of urban flooding with the extraction of building areas and estimates the its influence on flood inundation extent, and present initial results of flood simulation varying grid size.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.47 no.5
• /
• pp.63-71
• /
• 2005

In-situ soil remediation mechanism through the vertical drains (VDs) is analyzed with numerical model as the error and complementary error function. Results from in-situ test and analysis indicate that the contaminant concentration ratio as initial one ( C/$C_0$) increases as the radius ratio ( r/R) increases from the injection well, and also increases as the depth ratio ( z/ H) increases from the top of contaminated area. The elapse time needed to attain $50\%$ and $90\%$ clean up level ($ t_{50},\;t_{90}$) increases as the radius ratio ( r/R) and the depth ratio ( z/ H) increase. As above results, the procedure of soil flushing in contaminated area using vertical drains makes progress from the top of injection well to the bottom of extraction well.

• Journal of the Korean Society for Library and Information Science
• /
• v.56 no.3
• /
• pp.241-264
• /
• 2022

Bibliographic metadata can help researchers effectively utilize essential publications that they need and grasp academic trends of their own fields. With the manual creation of the metadata costly and time-consuming. it is nontrivial to effectively automatize the metadata construction using rule-based methods due to the immoderate variety of the article forms and styles according to publishers and academic societies. Therefore, this study proposes a two-step extraction process based on rules and deep neural networks for generating bibliographic metadata of scientific articlles to overcome the difficulties above. The extraction target areas in articles were identified by using a deep neural network-based model, and then the details in the areas were analyzed and sub-divided into relevant metadata elements. IThe proposed model also includes a model for generating reference summary information, which is able to separate the end of the text and the starting point of a reference, and to extract individual references by essential rule set, and to identify all the bibliographic items in each reference by a deep neural network. In addition, in order to confirm the possibility of a model that generates the bibliographic information of academic papers without pre- and post-processing, we conducted an in-depth comparative experiment with various settings and configurations. As a result of the experiment, the method proposed in this paper showed higher performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1086-1103
• /
• 2020

The automatic identification and classification of image-based weld defects is a difficult task due to the complex texture of the X-ray images of the weld defect. Several depth learning methods for automatically identifying welds were proposed and tested. In this work, four different depth convolutional neural networks were evaluated and compared on the 1631 image set. The concavity, undercut, bar defects, circular defects, unfused defects and incomplete penetration in the weld image 6 different types of defects are classified. Another contribution of this paper is to train a CNN model "RayNet" for the dataset from scratch. In the experiment part, the parameters of convolution operation are compared and analyzed, in which the experimental part performs a comparative analysis of various parameters in the convolution operation, compares the size of the input image, gives the classification results for each defect, and finally shows the partial feature map during feature extraction with the classification accuracy reaching 96.5%, which is 6.6% higher than the classification accuracy of other existing fine-tuned models, and even improves the classification accuracy compared with the traditional image processing methods, and also proves that the model trained from scratch also has a good performance on small-scale data sets. Our proposed method can assist the evaluators in classifying pipeline welding defects.

• Korean Journal of Remote Sensing
• /
• v.23 no.2
• /
• pp.119-124
• /
• 2007

The few observed data related snowmelt was the major cause of difficulty in extracting snowmelt factors such as snow cover area, snow depth and depletion curve. Remote sensing technology is very effective to observe a wide area. Although many researchers have used remote sensing for snow observation, there were a few discussions on the characteristics of spatial and temporal variation. Snow cover maps were derived from NOAA AVHRR images for the winter seasons from 1997 to 2006. Distributed snow depth was mapped by overlapping between snow cover maps and interpolated snowfall maps from 69 meteorological observation stations. Model parameters (Snow Cover Area: SCA, snow depth, Snow cover Depletion Curve: SDC) building for 5 major watersheds in South Korea. Especially SDC is important parameter of snowmelt model.

• Journal of The Geomorphological Association of Korea
• /
• v.26 no.2
• /
• pp.1-14
• /
• 2019

This study analyzed the relativity between block stream and talus distributions by employing a likelihood ratio approach. Possible distribution sites for each debris slope landform were extracted by applying a spatial integration model, in which we combined fuzzy set model, Bayesian predictive model, and logistic regression model. Moreover, to verify model performance, a success rate curve was prepared by cross-validation. The results showed that elevation, slope, curvature, topographic wetness index, geology, soil drainage, and soil depth were closely related to the debris slope landform sites. In addition, all spatial integration models displayed an accuracy of over 90%. The accuracy of the distribution potential area map of the block stream was highest in the logistic regression model (93.79%). Eventually, the accuracy of the distribution potential area map of the talus was also highest in the logistic regression model (97.02%). We expect that the present results will provide essential data and propose methodologies to improve the performance of efficient and systematic micro-landform studies. Moreover, our research will potentially help to enhance field research and topographic resource management.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.663-663
• /
• 2002

The National Oceanographic Research Institute of KOREA started to survey for the basic data necessary to territorial sea and EEZ identification and marine development with Multi-Beam Echo Sounder(L3 SeaBeam 2112) since 1996. The Multi-Beam surveys has provided a very new and precise way of describing the morphology and nature of the underwater seabed. Multi-Beam Echo Sounder systems employ sound waves propagating at angles which vary from vertical to nearly horizontal. The locations on the bottom where echoes are generated cover a swath whose port to starboard width may be equal to many times the water depth. Newer Multi-beam bathymetric sonars provide both a beam by beam depth and backscatter amplitude of the bottom. But The backscattered amplitude didn't use for identification of bottom properties because backscatter amplitude effects by the many environmental variables of underwater and seabed. We investigates the utilization of geo-referenced backscatter amplitude and analysis of relationship between The Backscattered Amplitude and Sidescan Sonar imagery from Sea Beam 2112. For the backscattered amplitude imagery mainly represents the properties of sediment, we computed the beam geometry, time-varied amplifier gain, and mainly incidence angle to the topography using bathymetric model at each ping. In this paper, those issues are illustrated, and the angular independent imagery based on swath topographic model is described.

• Journal of Korea Multimedia Society
• /
• v.8 no.4
• /
• pp.492-501
• /
• 2005

In this paper, we proposed the new segmentation method of optic nerve head and optic cub to consider the depth of optic nerve head on stereo fundus image. We analyzed the error factor of stereo matching on stereo fundus image, and compensated them. For robust extraction of optic nerve head and optic cub, we proposed the modified active contour model to consider the 3D depth of optic nerve head. As experiment result to various stereo fundus images, we confirmed that proposed method can segment optic nerve head and optic cup effectively.