• The Transactions of the Korea Information Processing Society
• /
• v.6 no.4
• /
• pp.868-876
• /
• 1999

In this paper, an efficient automatic video parsing technique on MPEG-compressed video that is fundamental for content-based indexing is described. The proposed method detects scene changes, regardless of IPB picture composition. To detect abrupt changes, the difference measure based on the dc coefficient in I picture and the macroblock reference feature in P and B pictures are utilized. For gradual scene changes, we use the macroblock reference information in P and B pictures. the process of scene change detection can be efficiently handled by extracting necessary data without full decoding of MPEG sequence. The performance of the proposed algorithm is analyzed based on precision and recall. the experimental results verified the effectiveness of the method for detecting scene changes of various MPEG sequences.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.2
• /
• pp.87-95
• /
• 2002

In this paper, we proposed a fast multi-resolution motion estimation(MRME) algorithm. This algorithm exploits the half-pixel accuracy motion estimation(HPAME) for exact motion vectors in the baseband and block classification for the reduction of bit amounts and computational loads. Generally, as the motion vector in the baseband are used as initial motion vector in the high frequency subbands, it has crucial effect on quality of the motion compensated image. For this reason, we exploit HPAME in the motion estimation for the baseband. But HPAME requires additional bit and computational loads so that we use block classification for the selective motion estimation in the high frequency subbands to compensate these problems. In result, we could reduce the bit rate and computational load at the similar image quality with conventional MRME. The superiority of the proposed algorithm was confirmed by the computer simulation.

• The Journal of the Korea Contents Association
• /
• v.19 no.1
• /
• pp.125-131
• /
• 2019

A vanishing point is a point on an image to which parallel lines projected from a real space gather. A vanishing point in a road space provides important spatial information. It is possible to improve the position of an extracted lane or generate a depth map image using a vanishing point in the road space. In this paper, we propose a method of detecting vanishing points on images taken from a vehicle's point of view using Deep Neural Network (DNN) and Histogram of Oriented Gradient (HoG). The proposed algorithm is divided into a HoG feature extraction step, in which the edge direction is extracted by dividing an image into blocks, a DNN learning step, and a test step. In the learning stage, learning is performed using 2,300 road images taken from a vehicle's point of views. In the test phase, the efficiency of the proposed algorithm using the Normalized Euclidean Distance (NormDist) method is measured.

• Journal of Digital Policy
• /
• v.2 no.3
• /
• pp.1-7
• /
• 2023

In this paper, I proposes a method for performing single image super resolution by separating texture-spatial domains and then classifying features based on detailed information. In CNN (Convolutional Neural Network) based super resolution, the complex procedures and generation of redundant feature information in feature estimation process for enhancing details can lead to quality degradation in super resolution. The proposed method reduced procedural complexity and minimizes generation of redundant feature information by splitting input image into two channels: texture and spatial. In texture channel, a feature refinement process with step-wise skip connections is applied for detail restoration, while in spatial channel, a method is introduced to preserve the structural features of the image. Experimental results using proposed method demonstrate improved performance in terms of PSNR and SSIM evaluations compared to existing super resolution methods, confirmed the enhancement in quality.

• Journal of KIISE:Software and Applications
• /
• v.33 no.4
• /
• pp.411-417
• /
• 2006

Motion Estimation (ME) is an important part of video coding process and it takes the largest amount of computation in video compression. Half-pixel and quarter-pixel motion estimation can improve the video compression rate at the cost of higher computational complexity In this paper, we suggest a new efficient low-complexity algorithm for half-pixel and quarter pixel motion estimation. It is based on the experimental results that the sum of absolute differences(SAD) shows parabolic shape and thus can be approximated by using interpolation techniques. The sub-pixel motion vector is searched from the minimum SAD integer-pixel motion vector. The sub-pixel search direction is determined toward the neighboring pixel with the lowest SAD among 8 neighbors. Experimental results show that more than 20% reduction in computation time can be achieved without affecting the quality of video.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.33-45
• /
• 2011

In this paper, we present a method for extracting video objects efficiently by using the modified graph cut algorithm based on contour information. First, we extract objects at the first frame by an automatic object extraction algorithm or the user interaction. To estimate the objects' contours at the current frame, motion information of objects' contour in the previous frame is analyzed. Block-based histogram back-projection is conducted along the estimated contour point. Each color model of objects and background can be generated from back-projection images. The probabilities of links between neighboring pixels are decided by the logarithmic based distance transform map obtained from the estimated contour image. Energy of the graph is defined by predefined color models and logarithmic distance transform map. Finally, the object is extracted by minimizing the energy. Experimental results of various test images show that our algorithm works more accurately than other methods.

• The KIPS Transactions:PartB
• /
• v.12B no.7 s.103
• /
• pp.729-736
• /
• 2005

In this paper. the proposed method for the digital watermarking is based on the multiresolution wavelet transform. The 1-level Discrete Wavelet Transform(DWT) coefficients of a $2N_{wx}{\times}2N_{wy}$ binary logo image used as a watermarks. The LL band and middle frequency band of the host image that the 3-level DWT has been performed are divided into $N_{wx}{\times}N_{wy}$ size and we use large coefficients at the divided blocks to make threshold. we set the thresholds that completely insert the watermark in each frequency of the host image. The thresholds in each frequency of the host image differ each other. The watermarks where is the same positions are added to the larger coefficients than threshold in the blocks at LL band and middle frequency band in order to prevent the quality deterioration of the host image. The watermarks are inserted in LL band and middle frequency band of the host image. In order to be invisibility of the watermark, the Human Visual System(HVS) is applied to the watermark. We prove the proper embedding method by experiment. We rapidly detect the watermark using this watermarking method. And because the small size watermarks are inserted by HVS, the results confirm the superiority of the proposed method on invisibility and robustness.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.7 s.361
• /
• pp.45-53
• /
• 2007

In this paper, we propose an efficient hardware architecture for H.264/AVC CAVLC (Context-based Adaptive Variable Length Coding) encoding. Previous CAVLC architectures search all of the coefficients to find statistic characteristics in a block. However, it is unnecessary information that zero coefficients following the last position of a non-zero coefficient when CAVLC encodes residual coefficients. In order to reduce this unnecessary operation, we propose two techniques, which detect the first and last position of non-zero coefficients and arrange non-zero coefficients sequentially. By adopting these two techniques, the required processing time was reduced about 23% compared with previous architecture. It was designed in a hardware description language and total logic gate count is 16.3k using 0.18um standard cell library Simulation results show that our design is capable of real-time processing for $1920{\times}1088\;30fps$ videos at 81MHz.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.4 s.42
• /
• pp.197-206
• /
• 2006

One of the most significant characteristics of JPEG2000. the emerging still image standards. is the ROI (Region of Interest) coding. JPEG2000 provides a number of ROI coding mechanisms and ROI parameters. To apply them to an application, it must select the applicable values. In this paper, we evaluate how the ROI coding mechanisms and the ROI parameters influencing JPEG2000 qualify affect the ROI quality and the whole image quality. The ROI coding mechanisms are Maxshift and Implicit. and the parameters are tile size and ROI size, codeblock size, number of DWT decomposition levels and ROI importance. The bigger the tile size, the better the quality. The bigger the ROI size, the ROI importance and the number of DWT decomposition levels, the worse the qualify. In code block $32{\times}32$ of Maxshift and Implicit, it has the best qualify.

• The KIPS Transactions:PartB
• /
• v.14B no.5
• /
• pp.321-328
• /
• 2007

In this paper, we propose a fast and dynamic Region-of-Interest coding method using the adaptive code-block discrimination algorithm in JPEG2000 images which complements the implicit ROI coding method and the modified implicit ROI coding method. For reducing the time of discriminating the code block, the proposed method estimates the characteristics of the shape of ROI and makes the shape of boundaries, and classifies the patterns of each code block. The method improves the preferred processing and loss of wavelet coefficients of background within the ROI code blocks by adaptively classifying the code blocks with the percentage of content of the wavelet coefficients using the thresholds of ROI and background. Also, the priority control of wavelet coefficients of background within ROI code block supports the rapid ROI coding by processing in batch based on patterns unlike the existing methods that process with unit of wavelet coefficients. To show the usefulness of this method, we compared this to the existing methods. There is no difference in performance, but we confirmed very speedy in processing time.