• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.217-220
• /
• 2022

본 논문에서는 CCTV 영상 화질을 향상하고 해상도를 높이기 위해 딥 러닝(Deep Learning)을 이용하여 잡음 제거(Denoising) 와 초해상도(Super-resolution) 작업을 수행한다. 데이터 증강(Data Augmentation)을 통한 초해상도 성능 향상을 위해서 잡음 제거 네트워크의 출력 영상을 초해상도 네트워크의 입력으로 사용하는 순차적 작업을 사용한다. 또한 딥 러닝을 이용한 영상처리에서 발생하는 평균 밝기 오차 문제를 해결하기 위한 손실함수(Loss Function)와 두 가지 이상의 순차적인 딥 러닝 작업에서 발생하는 문제점을 극복하기 위한 손실함수를 제안한다. 제안하는 손실함수는 네트워크의 출력 영상과 타겟 영상의 밝기 오차를 줄이는 것이 가능하고, 순차적 작업에서 보다 정확한 모델 성능 판단이 가능하다.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.230-240
• /
• 2022

Sharing of online videos via internet is an emerging and important concept in different types of applications like surveillance and video mobile search in different web related applications. So there is need to manage personalized web video retrieval system necessary to explore relevant videos and it helps to peoples who are searching for efficient video relates to specific big data content. To evaluate this process, attributes/features with reduction of dimensionality are computed from videos to explore discriminative aspects of scene in video based on shape, histogram, and texture, annotation of object, co-ordination, color and contour data. Dimensionality reduction is mainly depends on extraction of feature and selection of feature in multi labeled data retrieval from multimedia related data. Many of the researchers are implemented different techniques/approaches to reduce dimensionality based on visual features of video data. But all the techniques have disadvantages and advantages in reduction of dimensionality with advanced features in video retrieval. In this research, we present a Novel Intent based Dimension Reduction Semi-Supervised Learning Approach (NIDRSLA) that examine the reduction of dimensionality with explore exact and fast video retrieval based on different visual features. For dimensionality reduction, NIDRSLA learns the matrix of projection by increasing the dependence between enlarged data and projected space features. Proposed approach also addressed the aforementioned issue (i.e. Segmentation of video with frame selection using low level features and high level features) with efficient object annotation for video representation. Experiments performed on synthetic data set, it demonstrate the efficiency of proposed approach with traditional state-of-the-art video retrieval methodologies.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.8C
• /
• pp.1184-1192
• /
• 2004

A real-time pupil detection system that detects the pupil movement from the real-time video data achieved by the visual light camera for general purpose personal computer is proposed. It is implemented with three steps; at first, face region is detected using the Haar-like feature detection scheme, and then eye region is detected within the face region using the template-based scheme. Finally, pupil movement is detected within the eye region by convolution of the horizontal and vertical histogram profiling and Gaussian filter. As results, we obtained more than 90% of the detection rate from 2375 simulation images and the data processing time is about 160㎳, that detects 7 times per second.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.2
• /
• pp.775-792
• /
• 2015

Person re-identification is an important and challenging task in computer vision with numerous real world applications. Despite significant progress has been made in the past few years, person re-identification remains an unsolved problem. This paper presents a novel appearance-based approach to person re-identification. The approach exploits region covariance matrix and color histograms to capture the statistical properties and chromatic information of each object. Robustness against low resolution, viewpoint changes and pose variations is achieved by a novel signature, that is, the combination of Log Covariance Matrix feature and HSV histogram (LCMH). In order to further improve re-identification performance, third-party image sets are utilized as a common reference to sufficiently represent any image set with the same type. Distinctive and reliable features for a given image set are extracted through decision boundary between the specific set and a third-party image set supervised by max-margin criteria. This method enables the usage of an existing dataset to represent new image data without time-consuming data collection and annotation. Comparisons with state-of-the-art methods carried out on benchmark datasets demonstrate promising performance of our method.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.2E
• /
• pp.71-80
• /
• 2002

This paper suggests the Cardioid beamforming algorithm of the doublet sensors employing DIFAR (directional frequency analysis and recording) sensor signals in the frequency domain. The algorithm enables target bearing estimation using the signals from directional sensors. The algorithm verifies its applicability by successfully estimating bearings of a target projecting ten narrow-band signals in shallow water. The estimated bearings agree very well with those from GPS (global positioning system) data. Assuming the bearings from GPS data to be real values, the estimation errors are analyzed statistically. The histogram of estimation errors in each frequency have Gaussian shape, the mean and standard deviation dropping in the ranges -1.1°∼ 6.7°and 13.3∼43.6°, respectively. Estimation errors are caused by SNR (signal to noise ratio) degradation due to propagation loss between the source and receiver, daily fluctuating geo-magnetic fields, and non-stationary background noises. If multiple DIFAR systems are employed, in addition to bearing, range information could be estimated and finally localization or tracking of a target is possible.

• Journal of Biomedical Engineering Research
• /
• v.27 no.6
• /
• pp.409-417
• /
• 2006

Research on neural circuit is a difficult area due to complexity and inaccessibility. Due to recent developments, the research using multi-electrode array of cells or tissues has become an important research area. However, there are some difficulties to decode the submerged meaning from huge and complex neural data. Moreover, it needs a harmonic collaboration between informatics and bioscience. In this paper, we have developed a custom-designed signal processing technique for multi-electrode array measured neural responses induced by electrical stimuli to the hippocampal tissue slices of the rat brain. The raw data from hippocampal slice using the multi-electrode array system were saved in a computer. Then we estimated characteristic points in each channel and calculated the total activity. To estimate the points, we used the Polynomial Fitting Approximation Method. Using the calculated total activity, we could provide the histogram or pseudo-image matrix to help interpretation of results.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.2
• /
• pp.101-106
• /
• 2010

We propose an approach to estimate the real-time moving trajectory of an object in this paper. The object's position is obtained from the image data of a CCD camera, while a state estimator predicts the linear and angular velocities of the moving object. To overcome the uncertainties and noises residing in the input data, a Extended Kalman Filter(EKF) and neural networks are utilized cooperatively. Since the EKF needs to approximate a nonlinear system into a linear model in order to estimate the states, there still exist errors as well as uncertainties. To resolve this problem, in this approach the Kohonen networks, which have a high adaptability to the memory of the inputoutput relationship, are utilized for the nonlinear region. In addition to this, the Kohonen network, as a sort of neural network, can effectively adapt to the dynamic variations and become robust against noises. This approach is derived from the observation that the Kohonen network is a type of self-organized map and is spatially oriented, which makes it suitable for determining the trajectories of moving objects. The superiority of the proposed algorithm compared with the EKF is demonstrated through real experiments.

• Structural Engineering and Mechanics
• /
• v.17 no.5
• /
• pp.655-670
• /
• 2004

This paper aims to evaluate the effect of typhoons on fatigue damage accumulation in steel decks of long-span suspension bridges. The strain-time histories at critical locations of deck sections of long-span bridges during different typhoons passing the bridge area are investigated by using on-line strain data acquired from the structural health monitoring system installed on the bridge. The fatigue damage models based on Miner's Law and Continuum Damage Mechanics (CDM) are applied to calculate the increment of fatigue damage due to the action of a typhoon. Accumulated fatigue damage during the typhoon is also calculated and compared between Miner's Law and the CDM method. It is found that for the Tsing Ma Bridge case, the stress spectrum generated by a typhoon is significantly different than that generated by normal traffic and its histogram shapes can be described approximately as a Rayleigh distribution. The influence of typhoon loading on accumulative fatigue damage is more significant than that due to normal traffic loading. The increment of fatigue damage generated by hourly stress spectrum for the maximum typhoon loading may be much greater than those for normal traffic loading. It is, therefore, concluded that it is necessary to evaluate typhoon induced fatigue damage for the purpose of accurately evaluating accumulative fatigue damage for long-span bridges located within typhoon prone regions.

• Journal of the Korea Society of Computer and Information
• /
• v.3 no.4
• /
• pp.27-34
• /
• 1998

In this paper we present a method for automatic motion vector and brightness based video indexing and retrieval. We extract a representational frame from each shot and compute some motion vector and brightness based features. For each R-frame we compute the optical flow field; motion vector features are then derived from this flow field, BMA(block matching algorithm) is used to find motion vectors and Brightness features are related to the cut detection of method brightness histogram. A video database provided contents based access to video. This is achieved by organizing or indexing video data based on some set of features. In this paper the index of features is based on a B+ search tree. It consists of internal and leaf nodes stores in a direct access a storage device. This paper defines the problem of video indexing based on video data models.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.5 no.2
• /
• pp.169-184
• /
• 2002

In order to extract bearing information from the directional sensors of DIFAR(directional frequency analysis and recording) that is a kind of passive sonobuoy, the cardioid beamforming algorithm applicable to DIFAR system was studied in the frequency domain. the algorithm uses narrow-band signals propagated though the media from the acoustic sources such as ship machineries. The proposed algorithm is expected to give signal to noise ratio of 6dB when it uses the maximum response axis(MRA) among the Cardioid beams. The estimated bearings agree very well with those from GPS data. Assuming the bearings from GPS data to be real values, the estimation errors are analyzed statistically. The histogram of estimation errors in each frequency have Gaussian shape, the mean and standard deviation dropping in the ranges -1.1~$6.7^{\circ}$ and 13.3~$43.6^{\circ}$, respectively. Estimation errors are caused by SMR degradation due to propagation loss between the source and receiver, daily fluctuating geo-magnetic fields, and non-stationary background noises. If multiple DIFAR systems are employed, in addition to bearing, range information could be estimated and finally localization or tracking of a target is possible.