• Journal of Broadcast Engineering
• /
• v.22 no.1
• /
• pp.70-77
• /
• 2017

Among available people counting methods, map-based approaches based on moving interest points have shown good performance. However, the stationary people counting is challenging in such methods since all static points of interest are considered as background. To include stationary people in counting, it is needed to discriminate between the static points of stationary people and the background region. In this paper, we propose a people counting method based on using both moving and static points. The proposed method separates the moving and static points by motion information. Then, the static points of the stationary people are classified using foreground mask processing and point pattern analysis. The experimental results reveal that the proposed method provides more accurate count estimation by including stationary people. Also, the background updating is enabled to solve the static point misclassification problem due to background changes.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 1992.06a
• /
• pp.60-65
• /
• 1992

액정은 합성에 의해서 만들어지는 고분자 화합물로서 액체와 고체결정의 중간적인 특성을 갖는 물질이다. 따라서 액체와 같이 점도를 갖고 유동하며 고체와 같이 외부하중에 대하여는 탄성변형을 하므로 일반 윤활유보다 월등한 윤활특성이 기대된다. 액정은 분자배열에 따라 smectics, cholesterics, Nematics의 세종류로 나뉘어지며 Smectics는 다시 Smectic A, Smectic C등으로 분류되며 관심대상은 Smectic A이다. 본 연구에서는 평판 슬라이더 베어링의 간극에 액정층이 형성되어있을때 액정의 탄성계수, 침투계수 및 벌어짐계수가 베어링부하, 액정층의 유동현상등에 미치는 영향을 비선형 유한 요소법을 사용하여 해석하고 레이놀즈 이론해와 비교하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.613-615
• /
• 2011

본 논문에서는 켑스트럼 계수를 이용하여 음성인식을 하는 알고리즘을 제안한다. 본 논문에서 제안하는 방법은 사람이 발성한 음성을 두 영역의 켑스트럼 계수로 분리한 후에, 신경회로망을 사용하여 음성인식을 하는 방법이다. 본 논문에서 제안하는 신경회로망은 오차가 거의 없어지는 일정 기간 동안 네트워크를 학습시킨 후에 신경회로망의 학습 데이터와는 다른 새로운 음성이 신경회로망에 입력된 경우에 대하여 각 음성 구간에서 분류가 가능한 모음검출을 위한 음성인식 시스템을 제안한다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.4
• /
• pp.727-732
• /
• 2012

This paper presents an approach to classify normal and arrhythmia from the MIT-BIH Arrhythmia Database using Discrete Cosine Transform(DCT), Discrete Wavelet Transform(DWT) and neural network. In the first step, Discrete Cosine Transform is used to obtain the representative 15 coefficients for input features of neural network. In the second step, Discrete Wavelet Transform are used to extract maximum value, minimum value, mean value, variance, and standard deviation of detail coefficients. Neural network classifies normal and arrhythmia beats using 55 numbers of input features, and then the accuracy rate is 98.8%.

• Journal of the Korean GEO-environmental Society
• /
• v.13 no.4
• /
• pp.13-26
• /
• 2012

The deformation modulus of rock masses is a very important design factor for the computation of stability of tunnels and their support systems. Several empirical formulas to estimate the deformation modulus using simple rock classification methods such as RQD or RMR are widely used because field tests to evaluate the deformation modulus are very expensive and time consuming work. However, these formulas can be depended on experiences from the characteristics of local sites in each country. So it is possible that there might be limitations to estimate appropriate deformation modulus in South Korea using the empirical formulas. Therefore, in this study, the applicability of empirical formulas was analyzed by comparing estimated value with the measured value from eight sites in South Korea. The results show that the estimated value based on the empirical formulas partially have tendency to overestimate. Especially, in case of sedimentary rocks, it was too difficult to apply to the empirical formulas because there was no relation ship between estimated value and measured value. For these reasons, additional data from many tests and accurate analyses are necessary to evaluate the estimation method for the deformation modulus considering the local characteristics of rock masses.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.2
• /
• pp.28-38
• /
• 2000

This paper proposes a fractal compression method using the domain classification and local searching, which utilize DCT coefficient characteristic Generally, the fractal Image encoding method has a time consuming process to search a domain to be matched with range block In order to reduce computation complexity, the domain and range regions are respectively classified into 4 category by using the characteristics of DCT coefficients and each range region is encoded by a method suitable for the property of its category Since the bit amount of the compressed image depends on the number of range blocks, the matching of domain block and range block is induced on the large range block by using local search, so that compression ratio is increased by reducing the number of range block In the local search, the searching complexity is reduced by determining the direction and distance of searching using the characteristics of DCT coefficients The experimental results shows that the proposed algorithm have 1 dB higher PSNR and 0 806 higher compression ratio than previous algorithm.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.30 no.1
• /
• pp.28-37
• /
• 2019

In this paper, we propose a real-time system for counting people. The proposed system uses an impulse radio ultra-wideband(IR-UWB) radar to estimate the number of people in a given location. The proposed system uses learning-based classification methods to count people more accurately. In other words, a feature vector database is constructed by exploiting the pattern of reflected signals, which depends on the number of people. Subsequently, a classifier is trained using this database. When a newly received signal data is acquired, the system automatically counts people using the pre-trained classifier. We validated the effectiveness of the proposed algorithm by presenting the results of real-time estimation of the number of people changing from 0 to 10 in an indoor environment.

• 건축구조
• /
• v.12 no.5
• /
• pp.37-40
• /
• 2005

• Tunnel and Underground Space
• /
• v.18 no.6
• /
• pp.408-417
• /
• 2008

Rock mass classification methods such as RMR and Q system have different characteristics each other in parameters considered and applications, and so it is very important to prescribe the relationship between parameters for the analysis of correlativity of these methods. With the Held data of RMR and Q estimation in road construction sites, the acquaintance relations between RMR and Q of rock mass classifications are analyzed. The correlation equations between parameters of RMR and Q, matrix of correlation coefficients and the generalized form of acquaintance relation matrix are derived. This acquaintance relation matrix can be further extended to the form of generalized acquaintance relation network, and could be used to analyze the correlativity and to enhance the utility of common rock mass classification methods.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.2
• /
• pp.32-38
• /
• 2018

Studies on classification of national roads have been continued, but there is little research on the classification of urban arterial roads. Due to the increase of traffic volume, urban arterial roads do not perform well as main roads. In this paper, the function of urban arterial road was established by using cluster analysis using traffic characteristics. Traffic characteristics such as traffic volume, weekend coefficient and speed coefficient were used to establish the functions of 55 main arterial roads in Seoul. The results of this paper are compared with those of the method using AADT. The method using AADT classifies the characteristics according to the traffic volume of the whole lane. In this paper, however, the results are derived using the traffic volume per lane reflecting the actual traffic volume. In addition, the functional classification of the arterial roads in Seoul was compared with the results of this paper to verify that the traffic characteristics were reflected. As a result, the method presented in this paper is more effective in showing traffic characteristics than the current highway functional classification method, and the functional classification system will be helpful for road extension and planning design.