• Korean Journal of Remote Sensing
• /
• v.34 no.6_1
• /
• pp.1131-1142
• /
• 2018

The autonomous vehicles are being developed and operated widely because of the advantages of reducing the traffic accident and saving time and cost for driving. The vehicle localization is an essential component for autonomous vehicle operation. In this paper, localization algorithm based on sensor fusion is developed for cost-effective localization using in-vehicle sensors, GNSS, an image sensor and reference images that made in advance. Information of the reference images can overcome the limitation of the low positioning accuracy that occurs when only the sensor information is used. And it also can acquire estimated result of stable position even if the car is located in the satellite signal blockage area. The particle filter is used for sensor fusion that can reflect various probability density distributions of individual sensors. For evaluating the performance of the algorithm, a data acquisition system was built and the driving data and the reference image data were acquired. Finally, we can verify that the vehicle positioning can be performed with an accuracy of about 0.7 m when the route image and the reference image information are integrated with the route path having a relatively large error by the satellite sensor.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.1
• /
• pp.9-17
• /
• 2024

It is widely recognized that for 3D human pose estimation (HPE), dataset acquisition is expensive and the effectiveness of augmentation techniques of conventional visual recognition tasks is limited. We address these difficulties by presenting a simple but effective method that augments input images in terms of viewpoints when training a 3D human pose estimation (HPE) model. Our intuition is that meaningful variants of the input images for HPE could be obtained by viewing a human instance in the images from an arbitrary viewpoint different from that in the original images. The core idea is to synthesize new images that have self-occlusion and thus are difficult to predict at different viewpoints even with the same pose of the original example. We incorporate this idea into the training procedure of the 3D HPE model as an augmentation stage of the input samples. We show that a strategy for augmenting the synthesized example should be carefully designed in terms of the frequency of performing the augmentation and the selection of viewpoints for synthesizing the samples. To this end, we propose a new metric to measure the prediction difficulty of input images for 3D HPE in terms of the distance between corresponding keypoints on both sides of a human body. Extensive exploration of the space of augmentation probability choices and example selection according to the proposed distance metric leads to a performance gain of up to 6.2% on Human3.6M, the well-known pose estimation dataset.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.16 no.1
• /
• pp.122-131
• /
• 1992

An expert system is developed which can design the power transmission involute cylindrical gears on the basis of strength and durability. Bending strength, surface durability, scoring, and wear probability are considered as the basis. The basic components of the expert system are knowledge base, inference engine, and working memory. The knowledges in knowledge base are classified hierarchically into the knowledges used in selection of gear type, selection of materials, and determination of K factor and are represented by rules. In the inference engine two inference methods are implemented with the depth first search method. For-ward chaining method is introduced in the selection of gear type and materials and in the determination of K factor. Backward chaining method is introduced in the detailed design of module and face width in accordance with the validation of strength. And inference efficiency is achieved by constructing the part needing a lot of numerical calculations in strength estimation separately from inference mechanism. The working memory is established to save the results during inference temporarily. In addition, design database of past design results is built for consultation during design and knowledge acquisition facility, explanation facility, and user interface are included for the usefulness of user. This expert system is written with the PROLOG programming language and the FORTRAN language in numerical calculation part which interfaced with PROLOG and can also be executed on IBM-PC compatible computer operated by MS-DOS alone.

• The Journal of Society for e-Business Studies
• /
• v.22 no.1
• /
• pp.15-35
• /
• 2017

The method of weighted sum of evaluation using AHP is widely used in feasibility analysis and alternative selection. Final scores are given in forms of weighted sums and the alternative with largest score is selected. With two alternatives, as in feasibility analysis, the final score greater than 0.5 gives the selection but there remains a question that how large is large enough. KDI suggested a concept of 'grey area' where scores are between 0.45 and 0.55 in which decisions are to be made with caution, but it lacks theoretical background. Statistical testing was introduced to answer the question in some studies. It was assumed some kinds of probability distribution, but did not give the validity on them. We examine the various cases of weighted sum of evaluation score and show why the statistical testing has to be introduced. We suggest a non-parametric testing procedure which does not assume a specific distribution. A case study is conducted to analyze the validity of our suggested testing procedure. We conclude our study with remarks on the implication of analysis and the future way of research development.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.3
• /
• pp.189-204
• /
• 2018

This study has developed a forest fire occurrence probability model for inaccessible areas such as North Korea and Demilitarized Zone and we have developed a real-time forest fire danger rating system that can be used in fire-related works. There are limitations on the research that it is impossible to conduct site investigation for data acquisition and verification for forest fire weather index model and system development. To solve this problem, we estimated the fire spots in the areas where access is impossible by using MODIS satellite data with scientific basis. Using the past meteorological reanalysis data(5㎞ resolution) produced by the Korea Meteorological Administration(KMA) on the extracted fires, the meteorological characteristics of the fires were extracted and made database. The meteorological factors extracted from the forest fire ignition points in the inaccessible areas are statistically correlated with the forest fire occurrence and the weather factors and the logistic regression model that can estimate the forest fires occurrence(fires 1 and non-fores 0). And used to calculate the forest fire weather index(FWI). The results of the statistical analysis show that the logistic models(p<0.01) strongly depends on maximum temperature, minimum relative humidity, effective humidity and average wind speed. The logistic regression model constructed in this study showed a relatively high accuracy of 66%. These findings may be beneficial to the policy makers in Republic of Korea(ROK) and Democratic People's Republic of Korea(DPRK) for the prevention of forest fires.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.10
• /
• pp.48-54
• /
• 2020

DMSMS (Diminishing Manufacturing Sources and Material Shortage) is increased by developing the scientific technique and downsizing the military part market. DMSMS affects the increase in total life cycle costs and serviceability. Therefore, advance control for parts is important to reduce the cost, and a database is needed to share information on the DMSMS. A task needs to be performed continuously by setting the major control item to management more efficiently. The purpose of this study was to deduce the major control item for the DMSMS management system. Thus, the pre-control item basis of the DAPA (Defense Acquisition Program Administration) Manual and the SD-22 Manual were first selected, and the results of the survey were analyzed by AHP (Analytic Hierarchy Process) method. Fifteen of the detailed items were stratified into three criteria (Impact, Probability, and cost of the DMSMS), and each weight for the items was calculated using a nine-point scale survey. The AHP survey was executed with 25 specialists in the DMSMS management field, and the score of consistency ratio over 0.1 was excluded. The model explained the results and suggested future directions for development.

• Journal of KIISE
• /
• v.42 no.4
• /
• pp.451-458
• /
• 2015

Previous multimodal learning methods focus on problem-solving aspects, such as image and video search and tagging, rather than on knowledge acquisition via content modeling. In this paper, we propose the Multimodal Concept Hierarchy (MuCH), which is a content modeling method that uses a cartoon video dataset and a character-based subtitle generation method from the learned model. The MuCH model has a multimodal hypernetwork layer, in which the patterns of the words and image patches are represented, and a concept layer, in which each concept variable is represented by a probability distribution of the words and the image patches. The model can learn the characteristics of the characters as concepts from the video subtitles and scene images by using a Bayesian learning method and can also generate character-based subtitles from the learned model if text queries are provided. As an experiment, the MuCH model learned concepts from 'Pororo' cartoon videos with a total of 268 minutes in length and generated character-based subtitles. Finally, we compare the results with those of other multimodal learning models. The Experimental results indicate that given the same text query, our model generates more accurate and more character-specific subtitles than other models.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.12
• /
• pp.2511-2517
• /
• 2009

Recently, a FMCW radar is used for the various purposes in the short range detection and tracking of targets. The main advantages of a FMCWradar are the comparative simplicity of implementation and the low peak power transmission characterizing the very low probability of signal interception. Since it uses the frequency modulated continuous wave for transmission and demodulation, the received beat frequency represents the range and Doppler information of targets. Detection and extraction of useful information from targets are performed in this beat frequency domain. Therefore, the resolution and accuracy in the estimation of a beat spectrum are very important. However, using the conventional FFT estimation method, the high resolution spectrum estimation with a low sidelobe level is not possible if the acquisition time is very short in receiving target echoes. This kind of problems deteriorates the detection performance of adjacent targets having the large magnitude differences in return echoes and also degrades the reliability of the extracted information. Therefore, in this paper, the model parameter estimation methods such as autoregressive and eigenvector spectrum estimation are applied to mitigate these problems. Also, simulation results are compared and analyzed for further improvement.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.1
• /
• pp.22-30
• /
• 2015

Recently ITS have been increasingly applied on the roads to resolve traffic problems. Especially, Variable Message Sign (VMS), which is the one of ITS for traffic management and traffic safety, can be used for providing information about road conditions, climate conditions. In this study, data acquisition and statistical analysis were conducted for estimating safety impacts of providing traffic information through VMS. As a result of analyzing traffic characteristics before and after providing traffic information through VMS, average travel speed was decreased and vehicles tended to drive on centerline of lanes in 1st and 2nd lane after providing traffic information through VMS. Also, in order to analyze safety impacts of provided VMS traffic information, traffic safety hazard zone was established in each lane and probability distributions of passing traffic on the study area was estimated through Anderson-Darling Test. As a result of this, safety impacts of VMS traffic information in 1st lane could, on average, increase in left and right side of the lane by 0.69% and 7.07%, respectively. In case of 2nd lane, safety impacts could, on average, increase in left and right side of the lane by 2.71% and 0.02%, respectively.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.166-172
• /
• 2022

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.