• Journal of the Semiconductor & Display Technology
• /
• v.16 no.4
• /
• pp.30-35
• /
• 2017

Moving object segmentation from a nonstationary camera is a difficult problem due to the motion of both camera and the object. In this paper, we propose a new confidence-based background subtraction technique from moving camera. The method is based on clustering of motion vectors and generating adaptive multi-homography from a pair of adjacent video frames. The main innovation concerns the use of confidence images for each foreground and background motion groups. Experimental results revealed that our confidence-based approach robustly detect moving targets in sequences taken by a freely moving camera.

• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.19-32
• /
• 2007

This paper present a new face recognition method based on LVQ neural net to construct a real time face recognition system. The previous researches which used PCA, LDA combined neural net usually need much time in training neural net. The supervised LVQ neural net needs much less time in training and can maximize the separability between the classes. In this paper, the proposed method transforms the input face image by PCA and LDA sequentially into low-dimension feature vectors and recognizes the face through LVQ neural net. In order to make the system robust to external light variation, light compensation is performed on the detected face by max-min normalization method as preprocessing. PCA and LDA transformations are applied to the normalized face image to produce low-level feature vectors of the image. In order to determine the initial centers of LVQ and speed up the convergency of the LVQ neural net, the K-Means clustering algorithm is adopted. Subsequently, the class representative vectors can be produced by LVQ2 training using initial center vectors. The face recognition is achieved by using the euclidean distance measure between the center vector of classes and the feature vector of input image. From the experiments, we can prove that the proposed method is more effective in the recognition ratio for the cases of still images from ORL database and sequential images rather than using conventional PCA of a hybrid method with PCA and LDA.

• Journal of KIISE:Software and Applications
• /
• v.35 no.1
• /
• pp.1-11
• /
• 2008

This paper detected the characteristics of motion vector to support efficient content -based video search of video. Traditionally, the present frame of a video was divided into blocks of equal size and BMA (block matching algorithm) was used, which predicts the motion of each block in the reference frame on the time axis. However, BMA has several restrictions and vectors obtained by BMA are sometimes different from actual motions. To solve this problem, the foil search method was applied but this method is disadvantageous in that it has to make a large volume of calculation. Thus, as an alternative, the present study extracted the Spatio-Temporal characteristics of Motion Vector Spatio-Temporal Correlations (MVSTC). As a result, we could predict motion vectors more accurately using the motion vectors of neighboring blocks. However, because there are multiple reference block vectors, such additional information should be sent to the receiving end. Thus, we need to consider how to predict the motion characteristics of each block and how to define the appropriate scope of search. Based on the proposed algorithm, we examined motion prediction techniques for motion compensation and presented results of applying the techniques.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.10
• /
• pp.1845-1852
• /
• 2008

The key elements of inter prediction are motion estimation(ME) and motion compensation(MC). Motion estimation is to find the optimum motion vectors, not only by using a distance criteria like the SAD, but also by taking into account the resulting number of 비트s in the 비트 stream. Motion compensation is compensate for movement of blocks of current frame. Inter-prediction Encoding is always the main bottleneck in high-quality streaming applications. Therefore, in real-time streaming applications, dedicated hardware for executing Inter-prediction is required. In this paper, we studied a motion estimator(ME) for H.264/AVC. The designed motion estimator is based on 2-D systolic array and it connects processing elements for fast SAD(Sum of Absolute Difference) calculation in parallel. By providing different path for the upper and lower lesion of each reference data and adjusting the input sequence, consecutive calculation for motion estimation is executed without pipeline stall. With data reuse technique, it reduces memory access, and there is no extra delay for finding optimal partitions and motion vectors. The motion estimator supports variable-block size and takes 328 cycles for macro-block calculation. The proposed architecture is local memory-free different from paper [6] using local memory. This motion estimation encoder can be applicable to real-time video processing.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.5 s.311
• /
• pp.72-78
• /
• 2006

In this paper, we present a video shot retrieval algorithm in H.264/AVC compression domain. Unlike previous standards such as MPEG-2 and 4, H.264/AVC supports a variable block size for motion compensation. Therefore, existing video retrieval algorithms exploiting the motion vectors in MPEG-2 and 4 domains are not appropriate for H.264/AVC. So, we devise a method to project motion vectors with larger than $4{\times}4$ block sizes into those for the smallest $4{\times}4$ blocks. It also uses correlations among features for the measure of similarity. Experimental results with standard videos of 10558 frames and commercial videos of 48161 frames show that the proposed method yields ANMRR less than 0.2.

• Journal of KIISE:Software and Applications
• /
• v.32 no.6
• /
• pp.512-522
• /
• 2005

In this paper an algorithm of image alignments for constructing seamless mosaics is proposed. After the global alignment has been run, there may still be localized mis-registrations present in the mosaic. Due to mis-registrations, there may be seams in the mosaic, such as breaking, blurring, and doubling of lines. To solve this problem, we need an algorithm of residual motion estimation, which minimizes mis-registrations. In the conventional algorithms of residual motion estimation, computational powers are too heavy and estimators of camera parameters are additionally needed such as focal lengths. In the proposed algorithm, residual motion vectors are estimated with the adequate size of estimation and measurement windows and with adjustment of initial vectors according to the established priority. By construction of mosaics with the proposed algorithm, we demonstrate the removal of seams by mis-registrations.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.5
• /
• pp.135-142
• /
• 2009

Since hold-type display systems have been developed, frame-rate up conversion (FRUC) is an essential technique to improve the temporal resolution in the display. FRUC improves the temporal resolution by interpolating one or multiple intermediate frames between two adjacent frames. In this paper, a new frame-rate up-conversion algorithm based on bilateral motion refinement with rotation is proposed. First, we perform bi-directional motion estimation between adjacent two frames to obtain a motion vector for each block. Then, we apply a modified median filtering to motion vectors for outlier-rejection and motion field smoothing. The filtered motion vectors are updated by the bilateral motion refinement with rotation. After the refined motion vector is obtained, the intermediate frame is generated by applying the overlapped block motion compensation (OBMC). Experimental results show that the proposed algorithm provides a better performance than the previous methods subjectively and objectively.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.11 no.4
• /
• pp.293-301
• /
• 2006

This paper proposes a control algorithm for STATic synchronous COMpensator(STATCOM), based on Space Vector Modulation(SVM) and Hysteresis Current Controller(HCC) techniques. STATCOM is used to reactive power compensation on a distribution network. The proposed algorithm utilizes the advantages of the fast dynamic response of the hysteresis current control and the reduced switching number of the SVM scheme. The controller determines a set of space vectors from a region detector and applies a space vector. A set of space vectors including the zero vector, to reduce the number of switching, is determined from output signals of two hysteresis comparators. The presented control system was tested with digital simulation in the Borland C++ program and demonstrate the advantage of the proposed hysteresis current controller.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.1
• /
• pp.72-77
• /
• 2024

Recently, the necessity for sound source localization has grown significantly across various industrial sectors. Among the sound source localization methods, sound intensimetry has the advantage of having high accuracy even with a small microphone array. However, the increase in localization error at high Helmholtz numbers have been pointed out as a limitation of this method. The study proposes a method to compensate for the bias error of the measured sound intensity vector according to the Helmholtz numbers by applying deep learning. The method makes it possible to estimate the accurate direction of arrival of the source by applying a dense layer-based deep learning model that derives compensated sound intensity vectors when inputting the sound intensity vectors measured by a tetrahedral microphone array for the Helmholtz numbers. The model is verified based on simulation data for all sound source directions with 0.1 < kd < 3.0. One can find that the deep learning-based approach expands the measurement frequency range when implementing the sound intensimetry-based sound source localization method, also one can make it applicable to various microphone array sizes.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.6
• /
• pp.117-126
• /
• 2010

In the case of failure images with controlling lighting like backlighting and excessive frontlinghting, the compensation scheme for a specific area in an image is required. The interested region is first selected by user in our method to compensate the first frame. Then we define the matching function of brightness and energy function is proposed with weight of matching function and the relationship among the neighbors. Finally, the energy is minimized by the graph-cut algorithm to compensate the brightness of the first frame. Other frames are straightforwardly compensated using the results of the first frame. The brightness variations of the previous frame is transmitted to the next frame via motion vectors. The reliability of the brightness variation is calculated based on the motion vector reliability. Video compensation result is achieved by the process of the image case. Simulation show that the proposed algorithm provides more natural results than the conventional algorithms.