• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.260-270
• /
• 2023

We introduce a novel Visual Inertial Odometry (VIO) algorithm designed to improve the performance of thermal-inertial odometry. Thermal infrared image, though advantageous for feature extraction in low-light conditions, typically suffers from a high noise level and significant information loss during the 8-bit conversion. Our algorithm overcomes these limitations by approximating a 14-bit raw pixel histogram into a Gaussian mixture model. The conversion method effectively emphasizes image regions where texture for visual tracking is abundant while reduces unnecessary background information. We incorporate the robust learning-based feature extraction and matching methods, SuperPoint and SuperGlue, and zero velocity detection module to further reduce the uncertainty of visual odometry. Tested across various datasets, the proposed algorithm shows improved performance compared to other state-of-the-art VIO algorithms, paving the way for robust thermal-inertial odometry.

• Journal of the Korea Institute of Building Construction
• /
• v.13 no.5
• /
• pp.491-497
• /
• 2013

The objective of the present study is to establish a straightforward mixture proportioning procedure for structural lightweight aggregate concrete (LWAC), and evaluate the selection range of the targeted dry density of concrete against the designed concrete compressive strength. In developing this procedure, mathematical models were formulated based on a nonlinear regression analysis over 347 data sets and two boundary conditions of the absolute volume and dry density of concrete. The proposed procedure demonstrated the appropriate water-to-cement ratio and dry density of concrete to achieve the designed strength decrease with the increase in volumetric ratio of coarse aggregates. This trend was more significant in all-LWAC than in sand-LWAC. Overall, the selection range of the dry density of LWAC exists within a certain range according to the designed strength, which can be obtained using the proposed procedure.

• Journal of the Korea Institute of Building Construction
• /
• v.19 no.6
• /
• pp.503-510
• /
• 2019

Recently, construction technology of RC structures must be examined for creep in concrete. The factors affecting the creep prediction of concrete and the results of creep in domestic construction field were reviewed. The longer the creep test period and the higher the compressive strength, the higher the creep prediction accuracy. The higher the curing temperature, the higher the initial strength development of the concrete, but the difference in the creep coefficients increased over time. Based on the results of creep evaluation in the domestic construction field and lab. tests, a modified predictive model that complements the ACI-209 model was proposed. In the creep prediction of real members using general to high strength concrete, the test period and temperature should be considered precisely.

• Applied Chemistry for Engineering
• /
• v.18 no.2
• /
• pp.168-172
• /
• 2007

The separation of indole from a model mixture comprising four kinds of nitrogen heterocyclic compounds [indole (In), quinoline (Q), iso-quinoline (iQ), quinaldine (Qu)], three kinds of bicyclic aromatic compounds [1-methylnaphthalene (1MN), 2-methylnaphthalene (2MN), dimethylnaphthalene (DMN)], biphenyl (Bp) and phenyl ether (Pe) was examined by batch cocurrent 4 stages equilibrium extraction. The model mixture used as a raw material in this work was prepared according to the components and compositions contained in coal tar fraction (the temperature ranges of fraction: $240{\sim}265^{\circ}C$). An aqueous solution of formamide was used as a solvent. Indole was recovered more than 99% through 4 stages of the equilibrium extraction. The range of selectivity of indole in reference to DMN obtained through the 5 stages equilibrium extraction was found to be 63~118. The process for separation and recovery of indole contained in coal tar was studied by using the experimental results obtained from this work and the previous work.

• Journal of the Korean Institute of Gas
• /
• v.15 no.1
• /
• pp.60-67
• /
• 2011

The interest about new and renewable energy is increasing to reduce the burden of problems by depletion of fossil fuels and air pollutions. For example, LNG/CNG and LPG are expected to be replaced, especially in transportation use, by HCNG mixture and DME-LPG mixture, respectively. Because these new energies are still flammable gases, it is not inherently safe from the explosion. In this research, the quantitative risk analysis for using alternative mixtures in existing recharging facilities has been studied by using three types of explosion models (TNT equivalency model, PHAST and CFD-based FLACS) to manage the risk effectively. The differences of results by models were compared against, and the practical ways of when and how to use these models were suggested. It was also predicted that conventional gas filling stations would be converted as new energy stations without additional explosion risk.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.2
• /
• pp.395-406
• /
• 2017

The purpose of this study is to identify the pattern of daily electricity demand through clustering and classification. The hourly data was collected by KPS (Korea Power Exchange) between 2008 and 2012. The time trend was eliminated for conducting the pattern of daily electricity demand because electricity demand data is times series data. We have considered k-means clustering, Gaussian mixture model clustering, and functional clustering in order to find the optimal clustering method. The classification analysis was conducted to understand the relationship between external factors, day of the week, holiday, and weather. Data was divided into training data and test data. Training data consisted of external factors and clustered number between 2008 and 2011. Test data was daily data of external factors in 2012. Decision tree, random forest, Support vector machine, and Naive Bayes were used. As a result, Gaussian model based clustering and random forest showed the best prediction performance when the number of cluster was 8.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.6
• /
• pp.1293-1299
• /
• 2012

In this paper, a real-time vehicle detection and tracking algorithms is proposed. The vehicle detection could be processed using GMM (Gaussian Mixture Model) algorithm and mathematical morphological processing with HD CCTV camera images. The vehicle tracking based on separated vehicle object was performed using Euclidean distance between detected object. In more detail, background could be estimated using GMM from CCTV input image signal and then object could be separated from difference image of the input image and background image. At the next stage, candidated objects were reformed by using mathematical morphological processing. Finally, vehicle object could be detected using vehicle size informations dependent on distance and vehicle type in tunnel. The vehicle tracking performed using Euclidean distance between the objects in the video frames. Through computer simulation using recoded real video signal in tunnel, it is shown that the proposed system works well.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.11
• /
• pp.521-528
• /
• 2015

Road-view object classification methods are mostly influenced by weather and illumination conditions, thus the most of the research activities are based on dataset in clean weathers. In this paper, we present a road-view object classification method based on color segmentation that works for all kinds of weathers. The proposed method first classifies the weather and illumination conditions and then applies the weather-specified color models to find the road traffic signs. Using 5 different features of the road-view images, we classify the weather and light conditions as sunny, cloudy, rainy, night, and backlight. Based on the classified weather and illuminations, our model selects the weather-specific color ranges to generate Gaussian Mixture Model for each colors, Green, Yellow, and Blue. The proposed method successfully detects the traffic signs regardless of the weather and illumination conditions.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.5
• /
• pp.112-121
• /
• 1997

In this paper, we study a model parameter compensation method for noise-robust speech recognition. We study model parameter compensation on a sentence by sentence and no other informations are used. Parallel model combination(PMC), well known as a model parameter compensation algorithm, is implemented and used for a reference of performance comparision. We also propose a modified PMC method which tunes model parameter with an association factor that controls average variability of gaussian mixtures and variability of single gaussian mixture per state for more robust modeling. We obtain a re-estimation solution of environmental variables based on the expectation-maximization(EM) algorithm in the cepstral domain. To evaluate the performance of the model compensation methods, we perform experiments on speaker-independent isolated word recognition. Noise sources used are white gaussian and driving car noise. To get corrupted speech we added noise to clean speech at various signal-to-noise ratio(SNR). We use noise mean and variance modeled by 3 frame noise data. Experimental result of the VTS approach is superior to other methods. The scheme of the zero order VTS approach is similar to the modified PMC method in adapting mean vector only. But, the recognition rate of the Zero order VTS approach is higher than PMC and modified PMC method based on log-normal approximation.

• Fire Science and Engineering
• /
• v.25 no.3
• /
• pp.113-118
• /
• 2011

The flash point is an important indicator of the flammability of a chemical. The minimum flash point behaviour (MFPB) is exhibited when the flash point of a mixture is below the flash points of the individual components. The identification of this behaviour is critical, because a hazardous situation results from taking the lowest component flash point value as the mixture flash point. In this study, the flash points for the n-butanol + n-decane and n-octane + n-propanol systems which exhibit MFPB, were measured by Tag open-cup apparatus. The experimental data were compared with the alues calculated by the Raoult's law, the van Laar equation and the Wilson equation. The calculated values based on the van Laar and Wilson equations were found to be better than those based on the Raoult's law. It was concluded that the van Laar and Wilson equations were more effective than the Raoult' law at describing the activity coefficients for non-ideal solution such as the n-butanol + n-decane and n-octane + n-propanol systems. The predictive curve of the flash point prediction model based on the Wilson equation described the experimentally-derived data more effectively than was the case when the prediction model was based upon the van Laar equation.