• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.6
• /
• pp.44-56
• /
• 2008

Previous hardware devices to capture human motion have many limitations; expensive equipment, complexity of manipulation or constraints of human motion. In order to overcome these problems, real-time motion capture algorithms based on computer vision have been actively proposed. This paper presents an efficient analysis method of multiple view images for real-time motion capture. First, we detect the skin color regions of human being, and then correct the image coordinates of the regions by using camera calibration and epipolar geometry. Finally, we track the human body part and capture human motion using kalman filter. Experimental results show that the proposed algorithm can estimate a precise position of the human body.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.3
• /
• pp.11-19
• /
• 2008

Background subtraction, which separates moving objects in video sequences, is an essential technology for object recognition and tracking. However, background subtraction methods are often confused by shadow regions and this misclassification of shadow regions disturbs further processes to perceive the shapes or exact positions of moving objects. This paper proposes a method for shadow elimination which is based on shadow modeling by color information and Bayesian classification framework. Also, because of dynamic update of modeling parametres, the proposed method is able to correspond adaptively to illumination changes. Experimental results proved that the proposed method can eliminate shadow regions effectively even for circumstances with varying lighting condition.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.2
• /
• pp.99-105
• /
• 2017

Generally, stereo matching methods are used to estimate depth information based on color and spatial similarity. However, most depth estimation methods suffer from the occlusion region because occlusion regions cause inaccurate depth information. Moreover, they do not consider the temporal dimension when estimating the disparity. In this paper, we propose a temporal stereo matching method, considering occlusion and disregarding inaccurate temporal depth information. First, we apply a global stereo matching algorithm to estimate the depth information, we segment the image to occlusion and non-occlusion regions. After occlusion detection, we fill the occluded region with a reasonable disparity value that are obtained from neighboring pixels of the current pixel. Then, we apply a temporal disparity estimation method using the reliable information. Experimental results show that our method detects more accurate occlusion regions, compared to a conventional method. The proposed method increases the temporal consistency of estimated disparity maps and outperforms per-frame methods in noisy images.

• International Journal of Advanced Culture Technology
• /
• v.8 no.2
• /
• pp.96-100
• /
• 2020

In this paper, I try to help the business operation so that they could continue the desirable operation despite the unfavorable conditions. It is important to reinforce for corporate growth various support measures to generate profits. However, if they are involved in criminal activities such as slush fund creation, they will have to deal with them separately. As a result, To raise awareness helps to keep the company running. Recently, the companies are in a poor condition due to overseas migration. If a company does not create profits by doing business, it is a burden to continue operating and it will eventually be hard to support and destroy. The corporate crime and white-collar crime are mostly similar types, mainly because they occur in the industry. The corporate crime proceeds throughout the company and ultimately translates into corporate profits. The white-collar crime, on the other hand, is a profitable part of the individual. In the process of generating profits, the purpose and management method of slush funds is an important issue in judging whether illegal immorality of business is intended or not. In addition, in the case of the corporate crime, it seems necessary to identify the types of slush fund raising activities in addition to the investigations of the accomplices and clinical investigations, and to apply efficient investigation methods on a case-by-case basis. At present, many companies frequently migrate overseas due to the influence of domestic regulations. In this process, if it is involved in crime such as a borrowing accounts or the purpose of slush fund creation should be treated separately.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.5
• /
• pp.19-25
• /
• 2014

In this paper, I seek the chromatic number, the maximum number of colors necessary when adjoining vertices in the plane separated apart at the distance of 1 shall receive distinct colors. The upper limit of the chromatic number has been widely accepted as $4{\leq}{\chi}(G){\leq}7$ to which Hadwiger-Nelson proposed ${\chi}(G){\leq}7$ and Soifer ${\chi}(G){\leq}9$ I firstly propose an algorithm that obtains the minimum necessary chromatic number and show that ${\chi}(G)=3$ is attainable by determining the chromatic number for Hadwiger-Nelson's hexagonal graph. The proposed algorithm obtains a chromatic number of ${\chi}(G)=4$ assuming a Hadwiger-Nelson's hexagonal graph of 12 adjoining vertices, and again ${\chi}(G)=4$ for Soifer's square graph of 8 adjoining vertices. assert. Based on the results as such that this algorithm suggests the maximum chromatic number of a planar graph is ${\chi}(G)=4$ using simple assigned rule of polynomial time complexity to color for a vertex with minimum degree.

• The Korean Journal of Mycology
• /
• v.22 no.3
• /
• pp.216-221
• /
• 1994

As a part of studies on the fungal flora of Korea, authors have collected over 60 higher fungi specimens during summer season in 1993 in Mt. Hungjung which was located in eastern part of Korea. Among them two genera are new to Korea: Neobulgaria Petrak and Melastiza Boudier. Following five species are recorded for the first time in Korea: Psilocybe xeroderma Huijsm, Galerina vittaeformis (Fr.) Singer var. vittaeformis f. vittaeformis (Fr.) Singer, Gyromitra infula (Schaeffer ex Fries) Quelet, Neobulgaria pura (Fries) Petrak and Melastiza chateri (W. G. Smith) Boudier, for which Korean common names are designated in this present paper. All color names and terms within quotation marks are taken from Kornerup and Wanscher 1983, Methuen handbook of colour. The specimens are all deposited in the RDAGB's herbarium.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.18 no.36
• /
• pp.49-59
• /
• 1995

The vehicle navigation system is developed for helping driver to retrieve driving information more easily and fastly. Navigation System informs driver many pieces of driving information - roadway structure and system, on-line traffic condition, the position of vehicle, route guidance, destination and other information service. As the style of information is diverse and the amount of information is large, driver may have mental and visual overload. The display of information can disturb the driver's attention and this can cause accidents. This state is caused by the defect of human-machine interactions. When the navigation system is designed, human factors - cognitive, judgment, operating - must be considered. The display style must be designed simply and easily, not to be obstacle of human -machine interface. In this study, outside-in view display style and inside-out view display style are compared each other. Two factors are measured. One is cognitive factor-time of cognition on information that is displayed by screen display, cognition error rate. The other is image of screen display - subject's feeling about several styles of display, degree of subject's preference. The prototype of roadway is four kinds - Cross, T-cross, Y-cross and O-cross. Roadway display for test is taken from paper maps. Traffic condition display style, vehicle position display style and route guidance display style are taken from current display style. Traffic condition display style is symbol. Vehicle position display style and route guidance display style are described as color and symbol. The test on screen display is implemented doing given tasks. Then the test is analyzed statistically, The result of test analysis gives the guideline to the designer for the map display of the vehicle navigation system.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.2
• /
• pp.135-141
• /
• 2008

In this paper, we propose colored-hear recognition that distinguishing feature of synesthesia for human sensing by shared vision and specific sense of hearing. We perceived what potential influence of human's structured object recognition by visual analysis through the camera, So we've studied how to make blind persons can feel similar vision of real object. First of all, object boundaries are detected in the image data representing a specific scene. Then, four specific features such as object location in the image focus, feeling of average color, distance information of each object, and object area are extracted from picture. Finally, mapping these features to the audition factors. The audition factors are used to recognize vision for blind persons. Proposed colored-hear transformation for recognition can get fast and detail perception, and can be transmit information for sense at the same time. Thus, we were get a food result when applied this concepts to blind person's case of image recognition.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.3
• /
• pp.60-68
• /
• 2007

In this paper, we propose an automatic facial expressions recognition system to analyze facial expressions (happiness, disgust, surprise and neutral) using tree structures based on heuristic rules. The facial region is first obtained using skin-color model and connected-component analysis (CCs). Thereafter the origins of user's eyes are localized using neural network (NN)-based texture classifier, then the facial features using some heuristics are localized. After detection of facial features, the facial expression recognition are performed using decision tree. To assess the validity of the proposed system, we tested the proposed system using 180 facial image in the MMI, JAFFE, VAK DB. The results show that our system have the accuracy of 93%.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.20 no.1
• /
• pp.59-67
• /
• 2002

Recently, much demand of vector data have increased rapidly such as a digital map instead of traditional a paper map and the raster data such as a high-resolution orthoimage have been used for many GIS application with the advent of industrial high-resolution satellites and development of aerial optical sensor technologies. Aerial photogrammetric technologies using an airship can offer cost-effective and high-resolution color images as well as real time images, different from conventional remote sensing measurements. Also, it can acquire images easily and its processing procedure is short and simple relatively. On the other hand, it has often been used for the production of a small-scale land use map not required high accuracy, monitoring of linear infrastructure features through mosaicking strip images and construction of GIS data. Through this study, the developed aerial photogrammetric system using the airship expects to be applied to not only producing of scale 1:5, 000 digital map but also verifying, editing, and updating the digital map which was need to be reproduced. Further more, providing the various type of video-images, it expects to use many other GIS applications such as facilities management, scenery management and construction of GIS data for Urban area.