• Journal of information and communication convergence engineering
• /
• v.13 no.3
• /
• pp.197-204
• /
• 2015

In this paper, we present an algorithm for the detection of illegally parked vehicles based on a combination of some image processing algorithms. A digital camera is fixed in the illegal parking region to capture the video frames. An adaptive Gaussian mixture model (GMM) is used for background subtraction in a complex environment to identify the regions of moving objects in our test video. Stationary objects are detected by using the pixel-level features in time sequences. A stationary vehicle is detected by using the local features of the object, and thus, information about illegally parked vehicles is successfully obtained. An automatic alarm system can be utilized according to the different regulations of different illegal parking regions. The results of this study obtained using a test video sequence of a real-time traffic scene show that the proposed method is effective.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.3E
• /
• pp.91-97
• /
• 2004

In this paper, we propose a classification system of TV program scenes based on audio information. The system classifies the video scene into six categories of commercials, basketball games, football games, news reports, weather forecasts and music videos. Two type of audio feature set are extracted from each audio frame-timbral features and coefficient domain features which result in 58-dimensional feature vector. In order to reduce the computational complexity of the system, 58-dimensional feature set is further optimized to yield l0-dimensional features through Sequential Forward Selection (SFS) method. This down-sized feature set is finally used to train and classify the given TV program scenes using κ -NN, Gaussian pattern matching algorithm. The classification result of 91.6% reported here shows the promising performance of the video scene classification based on the audio information. Finally, the system stability problem corresponding to different query length is investigated.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.2
• /
• pp.52-61
• /
• 2006

For the detection of moving objects, background subtraction methods are widely used. An adaptive Gaussian mixture model combined with probabilistic learning is one of the most popular methods for the real-time update of the complex and dynamic background. However, probabilistic learning approach does not work well in high traffic regions. In this paper, we Propose a reliable learning method of complex and dynamic backgrounds in high traffic regions.

• MALSORI
• /
• no.63
• /
• pp.139-151
• /
• 2007

As the Internet becomes prevalent in our lives, harmful contents, such as phornographic videos, have been increasing on the Internet, which has become a very serious problem. To prevent such an event, there are many filtering systems mainly based on the keyword-or image-based methods. The main purpose of this paper is to devise a system that classifies pornographic videos based on the audio information. We use the mel-cepstrum modulation energy (MCME) which is a modulation energy calculated on the time trajectory of the mel-frequency cepstral coefficients (MFCC) as well as the MFCC as the feature vector. For the classifier, we use the well-known Gaussian mixture model (GMM). The experimental results showed that the proposed system effectively classified 98.3% of pornographic data and 99.8% of non-pornographic data. We expect the proposed method can be applied to the more accurate classification system which uses both video and audio information.

• The Journal of Industrial Distribution & Business
• /
• v.6 no.4
• /
• pp.27-37
• /
• 2015

Purpose - This study first explores the possible dynamic relationship between ownership structure and firm performance using a panel of 4,900 Chinese-listed small- and medium-sized enterprises (SMEs) from 1999 to 2012. Research design, data, and methodology - We address this issue through a dynamic panel model using a method of moments (GMM) technique and dynamic simultaneous equations to alleviate the potential endogenous problem: unobserved heterogeneity, simultaneity, and dynamic endogeneity. Results - Under the framework of dynamic endogeneity, firm performance has a significantly positive influence on ownership, but not vice versa. Ownership and performance can be explained by their owned lagged values, respectively. Moreover, intertemporal endogeneity exists among ownership, investment, and performance through the application of system dynamic equations, which implies that the relationship among ownership structure, investment, and firm performance is dynamic by nature. Conclusions - This study also significantly contributes to a better understanding of dynamic corporate governance by providing further empirical evidence from the largest capital market in the Asian region.

• Proceedings of the Safety Management and Science Conference
• /
• 2005.05a
• /
• pp.325-337
• /
• 2005

기존의 논문들은 단순히 기업가치(firm value)가 부채(debt)에 의한 요인들(determinants)에 의하여 좌우된다고 보았으며, 기업의 소유구조(managerial ownership)와 기업가치는 별개(exogenous)로 간주하여 왔다. 이 번 논문에서는 기업 가치를 좌우하는 요인들에 부채 이외에 기업의 소유구조를 내생변수(joint endogenous)로 추정하고, 통계방법으로는 수단변수를 사용하여 GMM(generalized method of moments)를 통하여 추정하기로 한다. 이 연구를 통해서는 부채와 기업 소유구조 사이에 밀접한 상호작용(interrelated)이 있음을 발견하였다. 부채와 기업의 소유구조를 내생화시킴으로써 이번 연구에서는 부채가 기업가치에 약한 부정적인(-) 영향을 주는 것으로 나타났으나, 기업의 소유구조는 기업 가치에 강한 긍정적 요인으로 작용하고 있음을 알 수 있었다. 이와 같이 부채와 기업가치의 약한 부정적인 관계에 대한 선행연구로는 Shea(1997)과 Hahn and Hausman(1999)이 있다. 또한, 기업가치는 시장점유율(market power)과 주가(treasury stock)와 양(+)의 관계에 있음을 알 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.2E
• /
• pp.56-62
• /
• 2007

This paper presents the automatic music emotion classification on acoustic data. A three-level structure is developed. The low-level extracts the timbre and rhythm features. The middle-level estimates the indication functions that represent the emotion probability of a single analysis unit. The high-level predicts the emotion result based on the indication function values. Experiments are carried out on 695 homogeneous music pieces labeled with four emotions, including pleasant, calm, sad, and excited. Three machine learning methods, GMM, MLP, and SVM, are compared on the high-level. The best result of 90.16% is obtained by MLP method.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.1
• /
• pp.29-37
• /
• 2005

This paper proposes an automatic genre classification system for Korean traditional music. The Proposed system accepts and classifies queried input music as one of the six musical genres such as Royal Shrine Music, Classcal Chamber Music, Folk Song, Folk Music, Buddhist Music, Shamanist Music based on music contents. In general, content-based music genre classification consists of two stages - music feature vector extraction and Pattern classification. For feature extraction. the system extracts 58 dimensional feature vectors including spectral centroid, spectral rolloff and spectral flux based on STFT and also the coefficient domain features such as LPC, MFCC, and then these features are further optimized using SFS method. For Pattern or genre classification, k-NN, Gaussian, GMM and SVM algorithms are considered. In addition, the proposed system adopts MFC method to settle down the uncertainty problem of the system performance due to the different query Patterns (or portions). From the experimental results. we verify the successful genre classification performance over $97{\%}$ for both the k-NN and SVM classifier, however SVM classifier provides almost three times faster classification performance than the k-NN.

• Phonetics and Speech Sciences
• /
• v.12 no.2
• /
• pp.29-37
• /
• 2020

Recently, the neural network-based deep learning algorithm has dramatically improved performance compared to the classical Gaussian mixture model based hidden Markov model (GMM-HMM) automatic speech recognition (ASR) system. In addition, researches on end-to-end (E2E) speech recognition systems integrating language modeling and decoding processes have been actively conducted to better utilize the advantages of deep learning techniques. In general, E2E ASR systems consist of multiple layers of encoder-decoder structure with attention. Therefore, E2E ASR systems require data with a large amount of speech-text paired data in order to achieve good performance. Obtaining speech-text paired data requires a lot of human labor and time, and is a high barrier to building E2E ASR system. Therefore, there are previous studies that improve the performance of E2E ASR system using relatively small amount of speech-text paired data, but most studies have been conducted by using only speech-only data or text-only data. In this study, we proposed a semi-supervised training method that enables E2E ASR system to perform well in corpus in different domains by using both speech or text only data. The proposed method works effectively by adapting to different domains, showing good performance in the target domain and not degrading much in the source domain.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.4
• /
• pp.343-350
• /
• 2016

In this paper, We proposed a realtime smoke detection using hidden markov model and DWT. The smoke type is not clear. The color of the smoke, form, spread direction, etc., are characterized by varying the environment. Therefore, smoke detection using specific information has a high error rate detection. Dynamic Object Detection was used a robust foreground extraction method to environmental changes. Smoke recognition is used to integrate the color, shape, DWT energy information of the detected object. The proposed method is a real-time processing by having the average processing speed of 30fps. The average detection time is about 7 seconds, it is possible to detect early rapid.