• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.206-214
• /
• 2022

The way to measure the extent of damage from floods and droughts is to identify changes in the extent of water systems. In order to effectively grasp this at a glance, satellite images are used. KOMPSAT-5 uses Synthetic Aperture Radar (SAR) to capture images regardless of weather conditions such as clouds and rain. In this paper, various deep learning models are applied to perform semantic segmentation of the water system in this SAR image and the performance is compared. The models used are U-net, V-Net, U2-Net, UNet 3+, PSPNet, Deeplab-V3, Deeplab-V3+ and PAN. In addition, performance comparison was performed when the data was augmented by applying elastic deformation to the existing SAR image dataset. As a result, without data augmentation, U-Net was the best with IoU of 97.25% and pixel accuracy of 98.53%. In case of data augmentation, Deeplab-V3 showed IoU of 95.15% and V-Net showed the best pixel accuracy of 96.86%.

• Asia-Pacific Journal of Business
• /
• v.14 no.1
• /
• pp.411-426
• /
• 2023

Purpose - The purpose of this study was to explore and diagnose the characteristics and behavioural patterns of rural tourists after COVID-19 using decision tree analysis to classify and identify key segmentation groups. Design/methodology/approach - The CHAID algorithm was used as the analysis technique for the decision tree. The explanatory variables used in the analysis of each decision tree model were demographic variables and rural tourism usage behaviour and perception variables, and the target variables were the preferences of rural tourists' activities after COVID-19. From the Rural Tourism 2020 survey data, 614 samples with rural tourism experience were extracted and used in the analysis. Findings - The variables that significantly explained the preference for each type of rural tourism activity after COVID-19 were rural tourism safety perception, repeated visits to the region, rural tourism priority activity, rural tourism accommodation experience, gender, age group, marital status, occupation, and education level. Among them, rural tourism safety perception was the most important explanatory variable in each analysis model. Research implications or Originality - Overall, to promote rural tourism, it is necessary to enhance the safety image of rural tourism, strengthen loyalty programs for repeat visitors, and develop customized products that reflect the preferred trends of rural tourism.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.6
• /
• pp.493-497
• /
• 2016

Infrared (IR) imaging is capable of detecting targets that are not visible at night, thus it has been widely used for the security and defense system. However, the quality of the IR image is often degraded by low resolution and noise corruption. This paper addresses target segmentation with the IR image. Multiple regions of interest (ROI) are extracted by the multi-level segmentation and targets are segmented from the individual ROI. Each level of the multi-level segmentation is composed of a k-means clustering algorithm an expectation-maximization (EM) algorithm, and a decision process. The k-means clustering algorithm initializes the parameters of the Gaussian mixture model (GMM) and the EM algorithm iteratively estimates those parameters. Each pixel is assigned to one of clusters during the decision. This paper proposes the selection and the merging of the extracted ROIs. ROI regions are selectively merged in order to include the overlapped ROI windows. In the experiments, the proposed method is tested on an IR image capturing two pedestrians at night. The performance is compared with conventional methods showing that the proposed method outperforms others.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.8
• /
• pp.243-252
• /
• 2023

Satellite imageries are at a greatest importance for land cover examining. Numerous studies have been conducted with satellite images and uses semantic segmentation techniques to extract information which has higher altitude viewpoint. The device which is taking these images must employee wireless communication links to send them to receiving ground stations. Wireless communications from a satellite are inevitably affected due to transmission errors. Evidently images which are being transmitted are distorted because of the information loss. Current semantic segmentation techniques are not made for segmenting distorted images. Traditional image enhancement methods have their own limitations when they are used for satellite images enhancement. This paper proposes an auto-encoder based image pre-enhancing method for satellite images. As a distorted satellite images dataset, images received from a real radio transmitter were used. Training process of the proposed auto-encoder was done by letting it learn to produce a proper approximation of the source image which was sent by the image transmitter. Unlike traditional image enhancing methods, the proposed method was able to provide more applicable image to a segmentation model. Results showed that by using the proposed pre-enhancing technique, segmentation results have been greatly improved. Enhancements made to the aerial images are contributed the correct assessment of land resources.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.108-115
• /
• 1996

This paper proposes an algorithm and a model topology for the connected speech recognition using Discrete Hidden Markov Models. A proposed model uses diphone and triphone model which consider the recognition rate and recognisable vocabulary. Considering more exact inter- phoneme segmentation and execution speed of algorithm, 4 states have to exist in diphone model where the first state and the last state are keeping a steady state, the other states hold a transient state. 7 states have to exist in triphone model where 7 states are specified and improved to 3 steady states and 4 transition states. Also, the proposed speech recognition algorithm is designed to detect the inter-phoneme segmentation during the recognition processing.

• The Journal of the Korea Contents Association
• /
• v.10 no.5
• /
• pp.210-219
• /
• 2010

Consumers differ in both horizontally and vertically. Market segmentation aims to divide horizontally different (or heterogeneous) consumers into more similar (or homogeneous) small segments. A specific consumer, however, may differ in vertically. He (or she) may belong to a different market segment from another one where he (or she) belonged to before. In consumer panel data, the vertical difference can be observed by his (or her) choice among brand alternatives are changing over time. The consumer's vertical difference has been defined as 'dynamics'. In this research, we have developed a binary probit model with random-walk coefficients to capture the consumer's dynamics. With an application to a consumer panel data, we have examined how have the random-walk coefficients changed over time.

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.2
• /
• pp.609-620
• /
• 2008

There may be several parallel equipments having the same function in a multi-stage manufacturing process, which affect the product quality differently and have significant differences in defect rate. The product quality may depend on what equipments it has been processed as well as what process variable values it has. Applying one model ignoring the presence of different equipments may distort the prediction of defect rate and the identification of important quality variables affecting the defect rate. We propose a procedure for data segmentation when constructing models for predicting the defect rate or for identifying major process variables influencing product quality. The proposed procedure is based on the principal component analysis and the analysis of variance, which demonstrates a better performance in predicting defect rate through a case study with a PDP manufacturing process.

• Proceedings of the Earthquake Engineering Society of Korea Conference
• /
• 2002.03a
• /
• pp.28-35
• /
• 2002

The probabilistic seismic hazard analysis for engineering needs several active fault parameters as input data. Fault slip rates, the segmentation model for each fault, and the date of the most recent large earthquake in seismic hazard analysis are the critical pieces of information required to characterize behavior of the faults. Slip rates provide a basis for calculating earthquake recurrence intervals. Segmentation models define potential rupture lengths and are inputs to earthquake magnitude. The most recent event is used in time-dependent probability calculations. These data were assembled by expert source-characterization groups consisting of geologists, geophysicists, and seismologists evaluating the information available for earth fault. The procedures to prepare inputs for seismic hazard are illustrated with possible segmentation scenarios of capable fault models and the seismic hazards are evaluated to see the implication of considering capable faults models.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.171-176
• /
• 1999

Intelligent schemes for an automatic generation of DEM (digital elevation model) are implemented. The need for these post-processing schemes is that interpolation alone produces severe blunders, however sophisticated it is. These blunders occur most seriously along the boundaries of a scene, over rivers, and along the coast. Even a state-of-the-art commercial software retains such blunders. The intelligent schemes implemented are (1) center-of-gravity and empty-center-index which quantify how evenly distributed interpolants are within in interpolation radius. (2) a segmentation scheme to discern whether or not an empty segment in stereo-match results should be interpolated, and (3) a segmentation scheme for removing noise-like features, with these methods, in the final DEM, identical coastline and river region to those in the original SPOT scenes are achieved. The DEM exhibits substantial improvements over the products of an existing commercial software.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.421-424
• /
• 1999

The purpose of this study is to demonstrate a variety of methods for reducing the speckle noise content of SAR images, whilst at the same time retaining the fined details and average radiometric properties of the original data. In order to increase the accuracy of classification, Two categories of filters are used (speckleblind(simple), Speckle aware(intelligent)) and Segmentation of highly speckled radar imagery is achieved by the use of the Gaussian Markov Random Field model(GMRF). The problems in applying filtering techniques to different object types are discussed and the GMRF procedure and efficiency of the segmentation also discussed.