• 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.

• Journal of Korea Game Society
• /
• v.9 no.5
• /
• pp.137-144
• /
• 2009

This paper predicts 6 facial regions that may have sharply different scattering properties, rendering the face more realistically based on their diffusion profiles. The scattering properties are acquired in the form of high dynamic range by photographing the pattern formed around an unit ray incident on facial skin. The acquired data are fitted to a 'linear combination of Gaussian functions', which well approximates the original diffusion profile of skin and has good characteristics as the filter. During the process, to prevent its solutions from converging into local minima, we take advantage of the genetic algorithm to set up the initial value. Each Gaussian term is applied to the irradiance map as a filter, expressing subsurface scattering effect. In this paper, to efficiently handle the maximum 12 Gaussian filterings, we make use of the parallel capacity of CUDA.

• Korean Journal of Remote Sensing
• /
• v.34 no.4
• /
• pp.625-638
• /
• 2018

In this paper, we derive i) a function to estimate snow cover fraction (SCF) from a MODIS satellite image that has a wide observational area and short re-visit period and ii) a function to determine snow depth from the estimated SCF map. The SCF equation is important for estimating the snow depth from optical images. The proposed SCF equation is defined using the Gaussian function. We found that the Gaussian function was a better model than the linear equation for explaining the relationship between the normalized difference snow index (NDSI) and the normalized difference vegetation index (NDVI), and SCF. An accuracy test was performed using 38 MODIS images, and the achieved root mean square error (RMSE) was improved by approximately 7.7 % compared to that of the linear equation. After the SCF maps were created using the SCF equation from the MODIS images, a relation function between in-situ snow depth and MODIS-derived SCF was defined. The RMSE of the MODIS-derived snow depth was approximately 3.55 cm when compared to the in-situ data. This is a somewhat large error range in the Republic of Korea, which generally has less than 10 cm of snowfall. Therefore, in this study, we corrected the calculated snow depth using the relationship between the measured and calculated values for each single image unit. The corrected snow depth was finally recorded and had an RMSE of approximately 2.98 cm, which was an improvement. In future, the accuracy of the algorithm can be improved by considering more varied variables at the same time.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.366-369
• /
• 2005

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

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.349-358
• /
• 2021

Recently, a method of finding the attention area or localization area for an object of an image using CAM (Class Activation Map)[1] has been variously carried out as a study of WSOL (Weakly Supervised Object Localization). The attention area extraction from the object heat map using CAM has a disadvantage in that it cannot find the entire area of the object by focusing mainly on the part where the features are most concentrated in the object. To improve this, using CAM and Selective Search[6] together, we first expand the attention area in the heat map, and a Gaussian smoothing is applied to the extended area to generate retraining data. Finally we train the data to expand the attention area of the objects. The proposed method requires retraining only once, and the search time to find an localization area is greatly reduced since the selective search is not needed in this stage. Through the experiment, the attention area was expanded from the existing CAM heat maps, and in the calculation of IOU (Intersection of Union) with the ground truth for the bounding box of the expanded attention area, about 58% was improved compared to the existing CAM.

• Korean Journal of Remote Sensing
• /
• v.32 no.6
• /
• pp.551-566
• /
• 2016

In the satellite remote sensing, the operational environment of the satellite sensor causes image degradation during the image acquisition. The degradation results in noise and blurring which badly affect identification and extraction of useful information in image data. Especially, the degradation gives bad influence in the analysis of images collected over the scene with complicate surface structure such as urban area. This study proposes a multi-stage image restoration to improve the accuracy of detailed analysis for the images collected over the complicate scene. The proposed method assumes a Gaussian additive noise, Markov random field of spatial continuity, and blurring proportional to the distance between the pixels. Point-Jacobian Iteration Maximum A Posteriori (PJI-MAP) estimation is employed to restore a degraded image. The multi-stage process includes the image segmentation performing region merging after pixel-linking. A dissimilarity coefficient combining homogeneity and contrast is proposed for image segmentation. In this study, the proposed method was quantitatively evaluated using simulation data and was also applied to the two panchromatic images of super-high resolution: Dubaisat-2 data of 1m resolution from LA, USA and KOMPSAT3 data of 0.7 m resolution from Daejeon in the Korean peninsula. The experimental results imply that it can improve analytical accuracy in the application of remote sensing high resolution panchromatic imagery.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.8
• /
• pp.818-822
• /
• 2008

The purpose of this study is to develop realistic painting simulation in real-time as well as to represent the thickness of the deposited paint on the surface. The Gaussian model is used for a painting deposition model to calculate the thickness of paints. For a painting simulation, rather than implementing particle systems, we propose a new heuristic algorithm for painting process based on a few number of rays. After we find the collision points of the rays with an environment, we compute the painted area using flood-fill searching method on the texture map and visualize paint effects. We analyzed time complexity of our method to verify that our system is suitable for real-time VR applications.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.7C
• /
• pp.587-593
• /
• 2010

In this paper we design an irregular low-density parity-check (LDPC) code for multiple-input multiple-output (MIMO) system, using a simple extrinsic information transfer (EXIT) chart method. The MIMO systems considered are optimal maximum a posteriori probability (MAP) detector. The MIMO detector and the LDPC decoder exchange soft information and form a turbo iterative receiver. The EXIT charts are used to obtain the edge degree distribution of the irregular LDPC code which is optimized for the MIMO detector. It is shown that the performance of the designed LDPC code is better than that of conventional LDPC code which was optimized for either the Additive White Gaussian Noise (AWGN) channel or the MIMO channel.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.1
• /
• pp.286-295
• /
• 2000

We present a novel statistically adaptive method using the Minimum Description Length(MDL) principle for unsupervised segmentation of magnetic resonance(MR) images. In the method, Markov random filed(MRF) modeling of tissue region accounts for random noise. Intensity measurements on the local region defined by a window are modeled by a finite Gaussian mixture, which accounts for image inhomogeneities. The segmentation algorithm is based on an iterative conditional modes(ICM) algorithm, approximately finds maximum ${\alpha}$ posteriori(MAP) estimation, and estimates model parameters on the local region. The size of the window for parameter estimation and segmentation is estimated from the image using the MDL principle. In the experiments, the technique well reflected image characteristic of the local region and showed better results than conventional methods in segmentation of MR images with inhomogeneities, especially.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.6
• /
• pp.736-747
• /
• 2006

Simultaneous Localization and Map Building(SLAM) is one of the fundamental problems in robot navigation. The Extended Kalman Filter(EKF), which is widely adopted in SLAM approaches, requires extensive computation. The conventional particle filter also needs intense computation to cover a high dimensional state space with particles. This paper proposes an efficient SLAM method based on the recursive unscented Kalman filtering in an environment including a large number of landmarks. The posterior probability distributions of the robot pose and the landmark locations are represented by their marginal Gaussian probability distributions. In particular, the posterior probability distribution of the robot pose is calculated recursively. Each landmark location is updated with the recursively updated robot pose. The proposed method reduces filtering dimensions and computational complexity significantly, and has produced very encouraging results for navigation experiments with noisy multiple simultaneous observations.