• Speech Sciences
• /
• v.9 no.2
• /
• pp.135-146
• /
• 2002

Generally a speaker verification system improves its system recognition ratio by regularizing log likelihood ratio, using a speaker model and its background speaker model that are required to be verified. The speaker-based cohort method is one of the methods that are widely used for selecting background speaker model. Recently, Gaussian-based cohort model has been suggested as a virtually synthesized cohort model, and unlike a speaker-based model, this is the method that chooses only the probability distributions close to basic speaker's probability distribution among the several neighboring speakers' probability distributions and thereby synthesizes a new virtual speaker model. It shows more excellent results than the existing speaker-based method. This study compared the existing speaker-based background speaker models and virtual speaker models and then constructed new virtual background speaker model groups which combined them in a certain ratio. For this, this study constructed a speaker verification system that uses GMM (Gaussin Mixture Model), and found that the suggested method of selecting virtual background speaker model shows more improved performance.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.159-161
• /
• 2004

Many motion object detection algorithms rely on the process of background subtraction, an important technique that is used for detecting changes from a model of the background scene. This paper propose a novel method to update the background model image of a visual surveillance system which is not stationary. In order to do this, we use a background model based on statistical qualities of monitored images and another background model that excluded motions. By comparing each changed area computed from the two background model images and current monitored image, the areas that will be updated are decided.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.3
• /
• pp.269-276
• /
• 2010

In this paper, we present the detection method of moving objects based on two background models. These background models support to understand multi layered environment belonged in images taken by shaking camera and each model is MBM(Multiple Background Model) and TMBM (Temporal Median Background Model). Because two background models are Pixel-based model, it must have noise by camera movement. Therefore correlation coefficient calculates the similarity between consecutive images and measures camera motion vector which indicates camera movement. For the calculation of correlation coefficient, we choose the selected region and searching area in the current and previous image respectively then we have a displacement vector by the correlation process. Every selected region must have its own displacement vector therefore the global maximum of a histogram of displacement vectors is the camera motion vector between consecutive images. The MBM classifies the intensity distribution of each pixel continuously related by camera motion vector to the multi clusters. However, MBM has weak sensitivity for temporal intensity variation thus we use TMBM to support the weakness of system. In the video-based experiment, we verify the presented algorithm needs around 49(ms) to generate two background models and detect moving objects.

• Speech Sciences
• /
• v.10 no.2
• /
• pp.35-43
• /
• 2003

General speaker verification systems improve their recognition performances by normalizing log likelihood ratio, using a speaker model and its background speaker model that are required to be verified. So these systems rely heavily on the availability of much speaker independent databases for background speaker model design. This constraint, however, may be a burden in practical and portable devices such as palm-top computers or wireless handsets which place a premium on computations and memory. In this paper, new approach for the GMM-based background model design used in portable speaker verification system is presented when the enrollment data is available. This approach is to modify three parameters of GMM speaker model such as mixture weights, means and covariances along with reduced mixture order. According to the experiment on a 20 speaker population from YOHO database, we found that this method had a promise of effective use in a portable speaker verification system.

• Journal of Korea Multimedia Society
• /
• v.11 no.5
• /
• pp.597-609
• /
• 2008

Due to the recursive updating nature of background model, previous background modeling methods are often perturbed by crowd scenes where foreground pixels occurs more frequently than background pixels. To resolve this problem, an adaptive background modeling method, which is based on the well-known Gaussian mixture background model, is proposed. In the proposed method, the learning rate of background model is adaptively adjusted with respect to the crowdedness of the scene. Consequently, the learning process is suppressed in crowded scene to maintain proper background model. Experiments on real dataset revealed that the proposed method could perform background subtraction effectively even in crowd situation while the performance is almost the same to the previous method in normal scenes. Also, the F-measure was increased by 5-10% compared to the previous background modeling methods in the video of crowded situations.

• Smart Media Journal
• /
• v.4 no.3
• /
• pp.50-55
• /
• 2015

In this paper, we present background modeling method based on Gaussian mixture model to subtract background for night-time video surveillance. In night-time video, it is hard work to distinguish the object from the background because a background pixel is similar to a object pixel. To solve this problem, we change the pixel of input frame to more advantageous value to make the Gaussian mixture model using scaled histogram stretching in preprocessing step. Using scaled pixel value of input frame, we then exploit GMM to find the ideal background pixelwisely. In case that the pixel of next frame is not included in any Gaussian, the matching test in old GMM method ignores the information of stored background by eliminating the Gaussian distribution with low weight. Therefore we consider the stacked data by applying the difference between the old mean and new pixel intensity to new mean instead of removing the Gaussian with low weight. Some experiments demonstrate that the proposed background modeling method shows the superiority of our algorithm effectively.

• Journal of applied mathematics & informatics
• /
• v.15 no.1_2
• /
• pp.511-525
• /
• 2004

we model communication and computer systems that process interactive and several and several types of background jobs. The scheduling policy in use is to share the processor among all interactive jobs and, at most, one background job of each type at a time according to the process sharing discipline. Background jobs of each type are served on a first-come-first-served basis. Such scheduling policy is called Processor Sharing with Background jobs (PSBJ). In fact, the PSBJ policy is commonly used on many communication and computer systems that allow interactive usage of the systems and process certain jobs in a background mode. In this paper, the stability conditions for the PSBJ policy are given and proved. Since an exact analysis of the policy seems to be very difficult, an approximate analytic model is proposed to obtain the average job sojourn times. The model requires the solution of a set of nonlinear equations, for which an iterative algorithm is given and its convergence is proved. Our results reveal that the model provides excellent estimates of average sojourn times for both interactive and background jobs with a few percent of errors in most of the cases considered.

• Geophysics and Geophysical Exploration
• /
• v.4 no.3
• /
• pp.84-88
• /
• 2001

For the elastic migation, the velocity errors between the initial velocity model and true velocity model seriously affect the migrated images. The assumption of an initial velocity model, thus, is one of the critical factor for the successful migration. In case of applying the layered earth model as an initial velocity model, the layer boundary having large velocity contrast can not be defined well with conventional traveltime calculation algolithms and we have the difficulties for expressing the characteristics of the real subsurface. Smooth Background Model (SBM) we have applied as an initial velocity model in our study is characterized to be linearly varying the velocity with the depth, which can express the velocity variation in the subsurface properly. Thus it can properly be applied to traveltime calculation algolithms such as Vidale's method. In this study, Kirchhoff operator for prestack migration was used and the absolute amplitude obtained by modeling was applied as a weighted value to consider the true amplitude for initial model. Initial velocity model for migration was determined by using stacking velocity and we applied this model to real data.

• MALSORI
• /
• no.56
• /
• pp.207-223
• /
• 2005

The goal of language model adaptation is to improve the background language model with a relatively small adaptation corpus. This study presents a language model adaptation technique where additional text data for the adaptation do not exist. We propose the information retrieval (IR) technique with N-gram language modeling to collect the adaptation corpus from baseline text data. We also propose to use a dynamic language model interpolation coefficient to combine the background language model and the adapted language model. The interpolation coefficient is estimated from the word hypotheses obtained by segmenting the input speech data reserved for held-out validation data. This allows the final adapted model to improve the performance of the background model consistently The proposed approach reduces the word error rate by $13.6\%$ relative to baseline 4-gram for two-hour broadcast news speech recognition.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.187-194
• /
• 2005

The background subtraction method is mainly used for the real-time extraction and tracking of moving objects from image sequences. In the outdoor environment, there are many changeable environment factors such as gradually changing illumination, swaying trees and suddenly moving objects , which are to be considered for an adaptive processing. Normally, GMM(Gaussian Mixture Model) is used to subtract the background by considering adaptively the various changes in the scenes, and the adaptive GMMs improving the real-time Performance were Proposed and worked. This paper, for on-line background subtraction, employed the improved adaptive GMM, which uses the small constant for learning rate a and is not able to speedily adapt the suddenly movement of objects, So, this paper Proposed and evaluated the dynamic control method of a using the adaptive selection of the number of component distributions and the global variances of pixel values.