• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.144-159
• /
• 2014

Techniques for making a single panoramic image using multiple pictures are widely studied in many areas such as computer vision, computer graphics, etc. The panorama image can be applied to various fields like virtual reality, robot vision areas which require wide-angled shots as an useful way to overcome the limitations such as picture-angle, resolutions, and internal informations of an image taken from a single camera. It is so much meaningful in a point that a panoramic image usually provides better immersion feeling than a plain image. Although there are many ways to build a panoramic image, most of them are using the way of extracting feature points and matching points of each images for making a single panoramic image. In addition, those methods use the RANSAC(RANdom SAmple Consensus) algorithm with matching points and the Homography matrix to transform the image. The SURF(Speeded Up Robust Features) algorithm which is used in this paper to extract featuring points uses an image's black and white informations and local spatial informations. The SURF is widely being used since it is very much robust at detecting image's size, view-point changes, and additionally, faster than the SIFT(Scale Invariant Features Transform) algorithm. The SURF has a shortcoming of making an error which results in decreasing the RANSAC algorithm's performance speed when extracting image's feature points. As a result, this may increase the CPU usage occupation rate. The error of detecting matching points may role as a critical reason for disqualifying panoramic image's accuracy and lucidity. In this paper, in order to minimize errors of extracting matching points, we used $3{\times}3$ region's RGB pixel values around the matching points' coordinates to perform intermediate filtering process for removing wrong matching points. We have also presented analysis and evaluation results relating to enhanced working speed for producing a panorama image, CPU usage rate, extracted matching points' decreasing rate and accuracy.

• The Journal of Society for e-Business Studies
• /
• v.25 no.2
• /
• pp.15-27
• /
• 2020

This study starts with the idea that the process of creating a Gantt Chart for schedule planning is similar to Tetris game with only a straight line. In Tetris games, the X axis is M machines and the Y axis is time. It is assumed that all types of orders can be worked without separation in all machines, but if the types of orders are different, setup cost will be incurred without delay. In this study, the game described above was named Gantris and the game environment was implemented. The AI-scheduling table through in-depth reinforcement learning compares the real-time scheduling table with the human-made game schedule. In the comparative study, the learning environment was studied in single order list learning environment and random order list learning environment. The two systems to be compared in this study are four machines (Machine)-two types of system (4M2T) and ten machines-six types of system (10M6T). As a performance indicator of the generated schedule, a weighted sum of setup cost, makespan and idle time in processing 100 orders were scheduled. As a result of the comparative study, in 4M2T system, regardless of the learning environment, the learned system generated schedule plan with better performance index than the experimenter. In the case of 10M6T system, the AI system generated a schedule of better performance indicators than the experimenter in a single learning environment, but showed a bad performance index than the experimenter in random learning environment. However, in comparing the number of job changes, the learning system showed better results than those of the 4M2T and 10M6T, showing excellent scheduling performance.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.177-190
• /
• 2021

Due to the development of the fourth industrial revolution technology, efforts are being made to improve areas that humans cannot handle by utilizing artificial intelligence techniques such as machine learning. Although on-demand production companies also want to reduce corporate risks such as delays in delivery by predicting total production time for orders, they are having difficulty predicting this because the total production time is all different for each order. The Theory of Constraints (TOC) theory was developed to find the least efficient areas to increase order throughput and reduce order total cost, but failed to provide a forecast of total production time. Order production varies from order to order due to various customer needs, so the total production time of individual orders can be measured postmortem, but it is difficult to predict in advance. The total measured production time of existing orders is also different, which has limitations that cannot be used as standard time. As a result, experienced managers rely on persimmons rather than on the use of the system, while inexperienced managers use simple management indicators (e.g., 60 days total production time for raw materials, 90 days total production time for steel plates, etc.). Too fast work instructions based on imperfections or indicators cause congestion, which leads to productivity degradation, and too late leads to increased production costs or failure to meet delivery dates due to emergency processing. Failure to meet the deadline will result in compensation for delayed compensation or adversely affect business and collection sectors. In this study, to address these problems, an entity that operates an order production system seeks to find a machine learning model that estimates the total production time of new orders. It uses orders, production, and process performance for materials used for machine learning. We compared and analyzed OLS, GLM Gamma, Extra Trees, and Random Forest algorithms as the best algorithms for estimating total production time and present the results.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.939-951
• /
• 2022

The most important factor in designing autonomous driving systems is to recognize the exact location of the vehicle within the surrounding environment. To date, various sensors and navigation systems have been used for autonomous driving systems; however, all have limitations. Therefore, the need for high-definition (HD) maps that provide high-precision infrastructure information for safe and convenient autonomous driving is increasing. HD maps are drawn using three-dimensional point cloud data acquired through a mobile mapping system (MMS). However, this process requires manual work due to the large numbers of points and drawing layers, increasing the cost and effort associated with HD mapping. The objective of this study was to improve the efficiency of HD mapping by segmenting semantic information in an MMS point cloud into six classes: roads, curbs, sidewalks, medians, lanes, and other elements. Segmentation was performed using various machine learning techniques including random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN), and gradient-boosting machine (GBM), and 11 variables including geometry, color, intensity, and other road design features. MMS point cloud data for a 130-m section of a five-lane road near Minam Station in Busan, were used to evaluate the segmentation models; the average F1 scores of the models were 95.43% for RF, 92.1% for SVM, 91.05% for GBM, and 82.63% for KNN. The RF model showed the best segmentation performance, with F1 scores of 99.3%, 95.5%, 94.5%, 93.5%, and 90.1% for roads, sidewalks, curbs, medians, and lanes, respectively. The variable importance results of the RF model showed high mean decrease accuracy and mean decrease gini for XY dist. and Z dist. variables related to road design, respectively. Thus, variables related to road design contributed significantly to the segmentation of semantic information. The results of this study demonstrate the applicability of segmentation of MMS point cloud data based on machine learning, and will help to reduce the cost and effort associated with HD mapping.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.35 no.2
• /
• pp.23-32
• /
• 2023

Probabilistic and deterministic analyses are implemented for the armor units of rubble foundation mound of composite breakwaters which is needed to protect the upright section against the scour of foundation mounds. By a little modification and incorporation of the previous empirical formulas that has commonly been applied to design the armor units of foundation mound, a new type formula of stability number has been suggested which is capable of taking into account slopes of foundation mounds, damage ratios of armor units, and incident wave numbers. The new proposed formula becomes mathematically identical with the previous empirical formula under the same conditions used in the developing process. Deterministic design have first been carried out to evaluate the minimum weights of armor units for several conditions associated with a typical section of composite breakwater. When the slopes of foundation mound become steepening and the incident wave numbers are increasing, the bigger armor units more than those from the previous empirical formula should be required. The opposite trends however are shown if the damage ratios is much more allowed. Meanwhile, the reliability analysis, which is one of probabilistic models, has been performed in order to quantitatively verify how the armor unit resulted from the deterministic design is stable. It has been confirmed that 1.2% of annual encounter probability of failure has been evaluated under the condition of 1% damage ratio of armor units for the design wave of 50 years return period. By additionally calculating the influence factors of the related random variables on the failure probability due to those uncertainties, it has been found that Hudson's stability coefficient, significant wave height, and water depth above foundation mound have sequentially been given the impacts on failure regardless of the incident wave angles. Finally, sensitivity analysis has been interpreted with respect to the variations of random variables which are implicitly involved in the formula of stability number for armor units of foundation mound. Then, the probability of failure have been rapidly decreased as the water depth above foundation mound are deepening. However, it has been shown that the probability of failure have been increased according as the berm width of foundation mound are widening and wave periods become shortening.

• Hwankyungkyoyuk
• /
• v.3 no.1
• /
• pp.130-140
• /
• 1992

The purpose of this study was to survey the trends of waste products in schools, its gathering and disposal, identification of problems and to analyze its disposal. Moreover, this study was aimed at basic suggestions about the establishment and plans of waste environmental education. 98 public primary and secondary schools were surveyed in Seoul during the month of March and April, 1991. Information was collected from each educational association by random sampling. Questionaries were used for this survey. To understand the disposal status of school waste and its reforms, this study surveyed the amount of waste by products, their origin and analyzed the disposal by type, one number of schools and teachers involved. The dump sited and disposal methods of school waste, its problems, and the status of school waste educations were researched, and ideal disposal methods and plans for waste education were suggested. The results were as follows. 1. The School's trash was produced by followings: paper, vinyle plastics, food, woods, metals, ceramics, glass, bottles, and ash from the heating system. The biggest cause of the school's waste as shown by the survey was a lack of environmental awareness(39.8%). The second biggest was the use of a one time use of disposable paper products(27.6%). 2. Waste collection by different grade levels were proven to be important but as you move from elementary to high school, the waste collecting operation decreased, in this connection between the students and waste collection itself it was significant on the other hand the teachers were not working as significant variables. 3. Of the school that collected waste 69.5 percent of the schools separately grouped common waste and recyclable waste. 25 schools(42.4%) received improvement on their environmental awareness of trash collection through this method. 4. From the number of disposal sites in surveyed schools, it was determined that the education of the necessity for separation of waste was performed in vain and accordingly the should require a real education in the future. 5. Regarding the method of disposal of waste the survey indicated that the #1 method of disposal was partial burning and the remains carried to a dump site by others(35,7%). In elementary schools the entire waste was taken by individuals to a dump site (33.3%). In high schools partial burning and then transported by individuals #1 in our survey(50%). 6. Relative to the problem of the treatment to waste, the emission of smoke from the burning was considered to be the #1 priority in our survey (62.3%) the problem of trash collection being delayed was 52.1%(1in our survey). 7. The present situation of environmental education of waste us lacking. Under present circumstances, the practice of public announcements for improvement and waste-paper collection has been going on vigorously but lacking in education as to the preparation of compositions for students the themes of public exhibitions, the organizing of voluntary associations should be part of the education system to reinforce student's awareness of proper waste disposal. 8. The most economical alternative for disposal was recycling usable waste or combustible material through a variety of education we can therefore educate students bring this education to their homes public servants will also be able to benefit in the waste disposal process with proper education. In conclusion we should intensify the systemical organization and the education of our waste disposal for a better environment.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.28 no.1
• /
• pp.153-160
• /
• 2010

It is necessary to determine accurate 3-dimensional coordinates of the building corner points that could be control or check points in order to verify the accuracy of 3D digital maps in the near future. The usual process of obtaining the coordinates of the building corner points is to set up the ground control points with a GPS and then to practice terrestrial survey such as distance or angle measurements. However, since an error in the ground control points can be propagated through the terrestrial survey into the final coordinates of the buildings, accurately should be considered as much as possible. The actual effect of the GPS-derived ground control point error on the estimates of the unknowns through the terrestrial survey is mathematically analyzed, and the simulation data is tested numerically. The error of the ground control points is tested in the cases of 1-4 cm for the horizontal components and 2-8 cm for the vertical component. The vertical component error is assigned twice the horizontal ones because of the characteristics of the GPS survey. The distance measurement is assumed for convenience and the precision of the estimated coordinates of the building corner points is almost linearly increased according to the errors of the ground control points. In addition, the final estimates themselves can vary by the simulated random errors depending on the precision of the survey instrument, but the precision of the estimates is almost independent of survey accuracy.

• Journal of KIISE:Software and Applications
• /
• v.27 no.5
• /
• pp.529-542
• /
• 2000

Recent years, the use of multimedia information is rapidly increasing, and the video media is the most rising one than any others, and this field Integrates all the media into a single data stream. Though the availability of digital video is raised largely, it is very difficult for users to make the effective video access, due to its length and unstructured video format. Thus, the minimal interaction of users and the explicit definition of video structure is a key requirement in the lately developing image and video management systems. This paper defines the terms and hierarchical video structure, and presents the system, which construct the clustering-based video hierarchy, which facilitate users by browsing the summary and do a random access to the video content. Instead of using a single feature and domain-specific thresholds, we use multiple features that have complementary relationship for each other and clustering-based methods that use normalization so as to interact with users minimally. The stage of shot boundary detection extracts multiple features, performs the adaptive filtering process for each features to enhance the performance by eliminating the false factors, and does k-means clustering with two classes. The shot list of a result after the proposed procedure is represented as the video hierarchy by the intelligent unsupervised clustering technique. We experimented the static and the dynamic movie videos that represent characteristics of various video types. In the result of shot boundary detection, we had almost more than 95% good performance, and had also rood result in the video hierarchy.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.9 no.4
• /
• pp.65-76
• /
• 2014

The basic purpose of this study is to examine the relationship among entrepreneurial intention, university supports for startup, and startup activities of university students. For the study, we identified the influence factors of students' startup intention based on reviewing preceding studies and examined how these factors affect their intention of new venture startup. In addition, this study attempted to examine how these factors that can have a significant impact on entrepreneurial intention affect startup activities and analyzed how entrepreneurial intention would mediate the relationship between these influence factors and startup activities. A total of 769 students who chosen by random were surveyed and all questionnaires were sent by mail to the universities that entrepreneurship education and entrepreneurial programs were selected as the forerunners from the government. As a result, this study revealed that student's psychological traits such as entrepreneurial self-efficacy and risk-taking have significant effect on the intention of startup. And student's exposure to the role models and various entrepreneurial experiences such as entrepreneurship education and entrepreneurial student's club in the university has significantly positive influence on the intention of startup. This study also found that the effects of these explanatory variables of this research on startup activities have been partially mediated by entrepreneurial intention. The entrepreneurial intention was also proven to have a significant effect on startup activities. Finally, the extent to which university supports activities for students' startup moderated the relationship between entrepreneurial intention and university students' startup activities. We believe that these results of this study contribute to the understanding of the entrepreneurship process both theoretical and practical perspectives.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.9 no.5
• /
• pp.21-31
• /
• 2014

The purpose of this study is to explore the relationships among service quality, self-efficacy, achievement need, and satisfaction in internet shopping mall entrepreneurial education. In this research, service quality consists of four factors including curriculum(lecturer expertise, distinction, and diversity of curricula), type(theory-oriented and practice-oriented), and administration(operation, facility and networking). First, this study investigated how service quality affected both self-efficacy and achievement need, second analyzed how both self-efficacy and achievement need influenced the satisfaction in internet shopping mall entrepreneurial education. The data were obtained from a questionnaire handed out to a random sample of 129 individuals that Cafe 24 in progress in the shopping mall entrepreneurial education. With the information obtained, and after the scales validation process, a structural equation analysis has been conducted. The analysis results indicate that service quality affects both self-efficacy and achievement need. According to the analysis, first, expertise, distinction and operation affect self-efficacy, second both expertise and operation affect achievement need. In addition, the results show that self-efficacy and achievement need influenced the satisfaction of entrepreneurial education. Finally, based in the findings of this study, theoretical contribution and managerial implications are discussed.