• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.10
• /
• pp.98-103
• /
• 1997

Given the small bit allocation for motion information in very low bit-rate coding, motion estimation using the block matching algorithm(BMA) fails to maintain an acceptable level of prediction errors. The reson is that the motion model, or spatial transformation, assumed in block matching cannot approximate the motion in the real world precisely with a small number of parameters. In order to overcome the drawback of the conventional block matching algorithm, several triangle-based methods which utilize triangular patches insead of blocks have been proposed. To estimate the motions of image sequences, these methods usually have been based on the combination of optical flow equation, affine transform, and iteration. But the compuataional cost of these methods is expensive. This paper presents a fast motion estimation algorithm using a multiple linear regression model to solve the defects of the BMA and the triange-based methods. After describing the basic 2-D triangle-based method, the details of the proposed multiple linear regression model are presented along with the motion estimation results from one standard video sequence, representative of MPEG-4 class A data. The simulationresuls show that in the proposed method, the average PSNR is improved about 1.24 dB in comparison with the BMA method, and the computational cost is reduced about 25% in comparison with the 2-D triangle-based method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.9
• /
• pp.1-6
• /
• 2019

One method for image recognition is template matching. In conventional template matching, the block matching algorithm (BMA) is performed while changing the two-dimensional translational displacement of the template within a given matching image. The template size and shape do not change during the BMA. Since only two-dimensional translational displacement is considered, the success rate decreases if the size and direction of the object do not match in the template and the matching image. In this paper, a variable is added to adjust the two-dimensional direction and size of the template, and the optimal value of the variable is automatically calculated in the block corresponding to each two-dimensional translational displacement. Using the calculated optimal value, the template is automatically transformed into an optimal template for each block. The matching error value of each block is then calculated based on the automatically deformed template. Therefore, a more stable result can be obtained for the difference in direction and size. For ease of use, this study focuses on designing the algorithm in a closed form that does not require additional information beyond the template image, such as distance information.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.8
• /
• pp.1792-1801
• /
• 2003

In these days, image mosaic is getting interest in the field of advertisement, tourism, game, medical imaging, and so on with the development of internet technology and the performance of personal computers. The main problem of mage mosaic is searching corresponding points correctly in the overlapped area between images. However, previous methods requires a lot of CPU times and data processing for finding corresponding points. And they need repeated recording with a revolution of 360 degree around objects or background. This paper presents a new image mosaic method which generates a panorama image from a video sequence recorded by a general video camera. Our method finds the corresponding points between two successive images by using a new direction oriented 3­step block matching methods. Experimental results show that the suggested method is more efficient than the methods based on existing block matching algorithm, such as full search and K­step search algorithm.

• Journal of Korea Multimedia Society
• /
• v.7 no.8
• /
• pp.1170-1182
• /
• 2004

A novel 4-way pipelined processing architecture is presented for three-step search block-matching motion estimation. For the 4-way pipelined processing, we have developed a method which divides the current block and search area into 4 subregions respectively and processes them concurrently. Also, we have developed memory partitioning method to access pixel data from 4 subregions concurrently without memory conflict. The architecture has been designed and simulated with C language and VHDL. Experimental results show that the proposed architecture achieves a high performance for real time motion estimation.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.9
• /
• pp.77-83
• /
• 1997

We present a fast adaptive block matching algorithm using variable search area and subsampling to estimate motion vector more exactly. In the presented method, the block is classified into one of three motion categories: zero motion vector block, medium-motion bolck or high-motion block according to mean absolute difference of the block. By the simulation, the computation amount of the presented methoe comparable to three step search algorithm and new three step search algorithm. In the fast image sequence, the PSNR of our algorithm increased more than TSS and NTSS, because our algorithm estimated motion vector more accurately.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.8C
• /
• pp.824-831
• /
• 2005

In the reconstruction of high resolution (HR) images from low resolution (LR) images frames, the error in the estimated motion degrades the reliability of the reconstructed HR image. Some methods were recently proposed where motion estimation and HR reconstruction is performed simultaneously. The estimated motion is still prone to error when it is based on a simple block matching. In this paper, we propose a reconstruction of a HR image by applying POCS and a regularized block matching simultaneously. In this method, a motion vector is obtained from a regularized block matching algorithm since the motion of a pixel in an image is highly correlated with the motion in neighboring regions. Experimental results show that the improved accuracy of the estimated motion vectors results in higher PSNR of the reconstructed HR images.

• Journal of Broadcast Engineering
• /
• v.16 no.6
• /
• pp.902-915
• /
• 2011

Recently in the area-based stereo matching field, Adaptive Support-Weight (ASW) method that weights matching cost adaptively according to the luminance intensity and the geometric difference shows promising matching performance. However, ASW requires more computational cost than other matching algorithms do and its real-time implementation becomes impractical. By applying Integral Histogram technique after approximating to the Bilateral filter equation, the computational time of ASW can be restricted in constant time regardless of the support window size. However, Integral Histogram technique causes loss of the matching accuracy during approximation process of the original ASW equation. In this paper, we propose a novel algorithm that maintains the ASW algorithm's matching accuracy while reducing the computational costs. In the proposed algorithm, we propose Sub-Block method that groups the pixels within the support area. We also propose the method adjusting the disparity search range depending on edge information. The proposed technique reduces the calculation time efficiently while improving the matching accuracy.

• Journal of Korea Multimedia Society
• /
• v.4 no.5
• /
• pp.406-413
• /
• 2001

Ordinary high-speed block matching algorithms have a disadvantage that they need to get MAD (Mean Absolute Distance) as many as the number of search points due to comparing the MAD between the current frame's search block and the reference frame's search block. To solve such disadvantage of high-speed block matching algorithm, the proposed high-speed DS algorithm employs a MMAD calculation method using a specific characteristic that neighboring pixels have almost same values. In this thesis, we can get rid of unnecessary MAD calculation between the search point block by the new calculation method which uses the previously calculated MAD as the current search point and by breaking from the established MAD calculation method which calculates the MAD of a new search point by each search stage. Comparing with the established high-speed block matching algorithm, this new calculation's estimated movement error was shown as similar, and th total calculation amount decreased by $2FN^2Ep$.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.300-301
• /
• 2011

본 논문에서는 Local Binary Pattern(LBP)과 Top-N Block Matching을 조합한 얼굴 인식 방법을 제안한다. 실제 상황에서 촬영된 얼굴영상에는 다양한 조명의 변화와 부분적인 가려짐의 영향을 크게 받기 때문에 실제 상황에서의 적용에 어려움이 있다. 따라서 기존의 LBP만을 이용한 얼굴 인식 방법은 좋은 성능을 보여주지 못한다. 이러한 문제를 극복하기 위해서 본 논문에서는 LBP와 Top-N Block Matching을 조합한 얼굴 인식 방법을 제안하였다. 제안된 얼굴 인식 방법이 기존의 LBP만을 사용한 얼굴 인식에 비해서 PF07 Database에서 약 7%의 성능향상이 이루어졌음을 실험을 통해서 보여주고 있다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.9B
• /
• pp.1697-1703
• /
• 1999

In this paper, we propose the fast block matching algorithm with half pel accuracy using the lower bound of mean absolute difference (MAD) at search point of half pel accuracy motion estimation. The proposed method uses the lower bound of MAD at search point of half pel accuracy which calculated from MAD's at search points of integer pel accuracy. We can reduce the computational complexity by executing the block matching operation only at the necessary search point. The points are selected when the lower bound of MAD at that point is smaller than reference MAD of integer pel motion estimation. Experimental results show that the proposed method can reduce the computational complexity considerably and keeping the same performance with conventional method.