• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.1
• /
• pp.169-189
• /
• 2015

Detection of anomalous events from video streams is a challenging problem in many video surveillance applications. One such application that has received significant attention from the computer vision community is traffic video surveillance. In this paper, a Lossy Count based Sequential Temporal Pattern mining approach (LC-STP) is proposed for detecting spatio-temporal abnormal events (such as a traffic violation at junction) from sequences of video streams. The proposed approach relies mainly on spatial abstractions of each object, mining frequent temporal patterns in a sequence of video frames to form a regular temporal pattern. In order to detect each object in every frame, the input video is first pre-processed by applying Gaussian Mixture Models. After the detection of foreground objects, the tracking is carried out using block motion estimation by the three-step search method. The primitive events of the object are represented by assigning spatial and temporal symbols corresponding to their location and time information. These primitive events are analyzed to form a temporal pattern in a sequence of video frames, representing temporal relation between various object's primitive events. This is repeated for each window of sequences, and the support for temporal sequence is obtained based on LC-STP to discover regular patterns of normal events. Events deviating from these patterns are identified as anomalies. Unlike the traditional frequent item set mining methods, the proposed method generates maximal frequent patterns without candidate generation. Furthermore, experimental results show that the proposed method performs well and can detect video anomalies in real traffic video data.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.3
• /
• pp.80-87
• /
• 2007

In this paper, we investigate an enhancement method for Western epigraphic images, which is based on local statistics. Image data is partitioned into two regions, background and information. Statistical and functional analyses are proceeded for image modeling. The Western epigraphic images, for the most part, have shown the Gaussian distribution. It is clarified that each region can be differentiated statistically. The local normalization process algorithm is designed on this model. The parameter is extracted and it‘s properties are verified with the size of moving window. The spatial gray-level distribution is modified and regions are differentiated by adjusting parameter and the size of moving window. Local statistics are utilized for realization of the enhancement, so that difference between regions can be enhanced and noise or speckles of region can be smoothed. Experimental results are presented to show the superiority of the proposed algorithm over the conventional methods.

• Journal of the Korea Society of Computer and Information
• /
• v.3 no.1
• /
• pp.81-94
• /
• 1998

In order to extract the contour of interesting object in the image, Kass suggested the Active Contour Model called "Snakes". Snakes is a model which defines the contour of image energy. It also can find the contour of object by minimizing these energy functions. The speed of this model is slow and this model is sensitive of initialization. In order to improve these problems, Gunn extracted the accurate contour by using two initialization. and operated to less sensitive of initialization. This method could extract more accurate contour than the existing method, but it had no effect in the speed and it was sensitive of noise. This paper applied to the Energy Minimization Algorithm about only the pixel within the window applying the window of 8$\times$8 size at each contour point consisting Snakes in order to solve these problems. The method offered in this paper is applied to extract the contour of original image and cup image added to gaussian noise. By tracking the face using this offered method, it is applied to virtual reality and motion tracking. tracking.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.8 no.3
• /
• pp.105-112
• /
• 1983

This paper discribes technique of the recursive restoration for the images degraded by linear space invariant blur and additive white Gaussian noise. The image is characterized statistically by tis mean and correlation function. An exponential autocorrelation function has been used to model neighborhood model. The vector model was used because of analytical simplicitly and capability to implement brightness correlation function. Base on the vector model, a two-dimensional discrete stochastic a 12 point neighborhood model for represeting images was developme and used the technique of moving window processing to restore blurred and noisy images without dimensionality increesing, It has been shown a 12 point neighborhood model was found to be more adequate than a 8 point pixel model to obtain optimum pixel estimated. If the image is highly correlated, it is necessary to use a large number of points in the neighborhood in order to have improvements in restoring image. It is believed that these result could be applied to a wide range of image processing problem. Because image processing thchniques normally required a 2-D linear filtering.

• Journal of information and communication convergence engineering
• /
• v.12 no.3
• /
• pp.168-172
• /
• 2014

In this paper, we propose an algorithm that can efficiently detect and monitor multiple ships in real-time. The proposed algorithm uses morphological operations and edge information for detecting and tracking ships. We used smoothing filter with a $3{\times}3$ Gaussian window and luminance component instead of RGB components in the captured image. Additionally, we applied Sobel operator for edge detection and a threshold for binary images. Finally, object labeling with connectivity and morphological operation with open and erosion were used for ship detection. Compared with conventional methods, the proposed method is meant to be used mainly in coastal surveillance systems and monitoring systems of harbors. A system based on this method was tested for both stationary and non-stationary backgrounds, and the results of the detection and tracking rates were more than 97% on average. Thousands of image frames and 20 different video sequences in both online and offline modes were tested, and an overall detection rate of 97.6% was achieved.

• Journal of Advanced Marine Engineering and Technology
• /
• v.24 no.2
• /
• pp.82-89
• /
• 2000

Edge detection is the first step and very important step in image analysis. In this paper, proposed edge detection operators based on informations of edge types and it is different from other classical edge detection operators such as gradient and surface fitting operators. The first, we defined characteristics of edge types such as localization, thinness, length. The second, we defined valid edge types and ideal edge pixel positions in $3\times3$window based on edge characteristics of edge types. And we proposed edge detection algorithm and twelve windows based on valid edge types. In specially, proposed algorithm was shown better performence of edge detection than other operators such as gradient operator and the LoG(Laplacian of Gaussian) operator of zero crossings.

• Journal of Korea Multimedia Society
• /
• v.16 no.12
• /
• pp.1368-1375
• /
• 2013

In this paper, we presents a spatially adaptive noise detection and removal algorithm. Under the assumption that an observed image and the additive noise have Gaussian distribution, the noise parameters are estimated with local statistics, and the parameters are used to define the constraints on the noise detection process, where the first order Markov Random Field (MRF) is used. In addition, an adaptive low-pass filter having a variable window sizes defined by the constraints on noise detection is used to control the degree of smoothness of the reconstructed image. Experimental results demonstrate the capability of the proposed algorithm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.797-800
• /
• 2003

In the current study, the authors propose a method for extracting license plate regions by means of a neural network trained to output the plates center of gravity. The method is shown to be effective. Since the learning pattern presentation positions are defined by random numbers, a different pattern is submitted to the neural network for learning each time, which enables it to form a neural network with high universality of coverage. The article discusses issues of the optimal learning surface for a license plate revered by the learning pattern, the effort of suppression learning of the number and headlight sections, as well as the effect of learning pattern enlargement/reduction and of concentration value conversion. Results of evaluation tests based on pictures of 595 vehicles taken at an underground parking garage demonstrated detection rates of 98.5%.

• Korea-Australia Rheology Journal
• /
• v.18 no.4
• /
• pp.199-207
• /
• 2006

Measurements by Luap et al. (2005) of elongational viscosity and birefringence of two nearly monodisperse polystyrene melts with molar masses $M_{w}$ of $206,000g{\cdot}mol^{-1}$ (PS206k) and $465,000g{\cdot}mol^{-1}$ (PS465k) respectively are reconsidered. At higher elongational stresses, the samples showed clearly deviations from the stress optical rule (SOR). The elongational viscosity data of both melts can be modeled quantitatively by the MSF model of Wagner et al. (2005), which is based on the assumption of a strain-dependent tube diameter and the interchain pressure term of Marrucci and Ianniruberto (2004). The only nonlinear parameter of the model, the tube diameter relaxation time, scales with $M_{w}^{2}$. In order to get agreement with the birefringence data, finite chain extensibility effects are taken into account by use of the $Pad\'{e}$ approximation of the inverse Langevin function, and the interchain pressure term is modified accordingly. Due to a selfregulating limitation of chain stretch by the FENE interchain pressure term, the transient elongational viscosity shows a small dependence on finite extensibility only, while the predicted steady-state elongational viscosity is not affected by non-Gaussian effects in agreement with experimental evidence. However, deviations from the SOR are described quantitatively by the MSF model by taking into account finite chain extensibility, and within the experimental window investigated, deviations from the SOR are predicted to be strain rate, temperature, and molar mass independent for the two nearly monodisperse polystyrene melts in good agreement with experimental data.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.70-75
• /
• 1998

The comparison of Topex/Poseidon sea surface heights and Tide Gauge sea levels was studied in the South Indian Ocean after Topex/Poseidon mission of about 3 years (11- 121 cycles) from January 1993 through December 1995. The user's handbook (AVISO) for sea surface height data process was used in this study Topex/Poseidon sea suface heights ($\zeta$$^{T/P}$), satellite data at the point which is very closed to Tide Gauge station, were chosen in the same latitude of Tide Gauge station. These data were re-sampled by a linear interpolation with the interval of about 10 days, and were filtered by the gaussian filter with a 60 day-window. Tide Gauge sea levels ($\zeta$$^{Argos}$, $\zeta$$^{In-situ}$ and $\zeta$$^{Model}$), were also treated with the same method as satellite data. The main conclusions obtained from the root-mean-square and correlation coefficient were as follows: 1) to Produce Tide Gauge sea levels from bottom pressure, in-situ data of METEO-FRANCE showed very good values against to the model data of ECMWF and 2) to compare Topex/Poseidon sea surface heights of Tide Gauge sea levels, the results of the open sea areas were better than those of the coast and island areas.