• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.533-538
• /
• 2008

본 논문에서는 GPU의 성능을 이용하여 다시점 거리 영상을 실시간으로 정합하는 3차원 온라인 시스템을 제안한다. 제안한 시스템은 거리영상의 정교한 정합을 위해 IPP 알고리즘을 사용하였으며, 최신 GPU 프로그래밍 기법으로 각광받고 있는 CUDA를 이용하여 정합 알고리즘의 연산비용이 큰 부분에 해당하는 투영과 변환의 반복 부분을 수행하였다. 스테레오 기반 휴대용 거리센서에서 $320{\times}240$ 거리영상을 획득하여 정합 알고리즘을 수행한 결과, 초당 5장의 거리영상을 정합할 수 있었다. 제안한 온라인 시스템은 실시간 3차원 모델 복원 기술이 필요한 로봇위치 인식, 주행용 비전 기술, 문화재 원형 복원 등의 분야에서 활용될 수 있을 것이다.

• Journal of Broadcast Engineering
• /
• v.16 no.5
• /
• pp.861-872
• /
• 2011

Many fast block-matching algorithms (BMAs) in motion estimation field reduce computational complexity by screening the number of checking points. Although many fast BMAs reduce computations, sometimes they should endure matching errors in comparison with full-search algorithm (FSA). In this paper, a novel fast BMA for constrained one-bit transform (C1BT)-based motion estimation is proposed in order to decrease the calculations of the block distortion measure. Unlike the classical fast BMAs, the proposed algorithm shows a new approach to reduce computations. It utilizes the binomial distribution based on the characteristic of binary plane which is composed of only two elements: 0 and 1. Experimental results show that the proposed algorithm keeps its peak signal-to-noise ratio (PSNR) performance very close to the FSA-C1BT while the computation complexity is reduced considerably.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.11a
• /
• pp.191-194
• /
• 2000

일반 적인 고속 블록 정합 알고리즘들은 현재 프레임의 탐색 블록과 참조 프레임의 탐색영역 내의 블록간 MAD(Mean Absolute Distance)를 구하여 그 값을 탐색 점으로 사용하므로 탐색 점 수만큼 MAD를 구해야 하는 단점이 있다. 이와 같은 고속 블록 정합 알고리즘들의 단점을 해결하기 위해 탐색 점 예측에 의한 고속 블록 정합 알고리즘을 제안한다. 본 논문에서는 "이웃 한 화소는 서로 간에 거의 같은 값을 지니고 있다"라는 성질을 이용하여, 이웃 한 탐색 점 두개의 MAD 평균값을 계산하여 그 값을 새로운 탐색 점으로 사용하여 탐객 하기 때문에 탐색 점 수는 DS(Diamond Search)알고리즘과 비교하여 비슷하지만, 최소 오차가 center일 때의 탐색 점을 예측에 의해 산출 하므로 총 연산량은 2Ep$N_2$만큼 크게 줄어든다. Ep는 예측 탐색 점 수를 나타내며, N은 블록의 크기를 나타낸다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.9
• /
• pp.2007-2012
• /
• 2011

To reduce huge computation in the block matching, this paper proposes a fast block matching algorithm which limits search points in the search area. On the basis of two facts that most motion vectors are located in central part of search area and matching error is monotonic decreasing toward the best similar block, the proposed algorithm moves a matching pattern between steps by the one pixel, predicts the motion direction for the best similar block from similar blocks decided in previous steps, and limits movements of search points to ${\pm}45^{\circ}C$ on it. As a result, it could remove the needless search points and reduce the block matching computation. In comparison with the conventional similar algorithms, the proposed algorithm caused the trivial image degradation in images with fast motion but kept the equivalent image quality in images with normal motion, and it, meanwhile, reduced from about 20% to over 67% of the their block matching computation.

• Journal of KIISE:Software and Applications
• /
• v.37 no.1
• /
• pp.9-18
• /
• 2010

This paper proposes a deformable registration method using a demon algorithm for aligning the lungs between end-exhale and end-inhale CT scans. The lungs are globally aligned by affine transformation and locally deformed by a demon algorithm. The use of floating gradient force allows a fast convergence in the lung regions with a weak gradient of the reference image. The active-cell-based demon algorithm helps to accelerate the registration process and reduce the probability of deformation folding because it avoids unnecessary computation of the displacement for well-matched lung regions. The performance of the proposed method was evaluated through comparisons of methods that use a reference gradient force or a combined gradient force as well as methods with and without active cells. The results show that the proposed method can accurately register lungs with large deformations and can reduce the processing time considerably.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.475-491
• /
• 2021

With the recent increase in available high-resolution (< ~1 m) satellite SAR images, the demand for precise registration of SAR images is increasing in various fields including change detection. The registration between high-resolution SAR images acquired in different look angle is difficult due to speckle noise and geometric distortion caused by the characteristics of SAR images. In this study, registration is performed in two stages, coarse and fine, using the x-band SAR data imaged at staring spotlight mode of TerraSAR-X. For the coarse registration, a method combining the adaptive sampling method and SAR-SIFT (Scale Invariant Feature Transform) is applied, and three rigid methods (NCC: Normalized Cross Correlation, Phase Congruency-NCC, MI: Mutual Information) and one non-rigid (Gefolki: Geoscience extended Flow Optical Flow Lucas-Kanade Iterative), for the fine registration stage, was performed for performance comparison. The results were compared by using RMSE (Root Mean Square Error) and FSIM (Feature Similarity) index, and all rigid models showed poor results in all image combinations. It is confirmed that the rigid models have a large registration error in the rugged terrain area. As a result of applying the Gefolki algorithm, it was confirmed that the RMSE of Gefolki showed the best result as a 1~3 pixels, and the FSIM index also obtained a higher value than 0.02~0.03 compared to other rigid methods. It was confirmed that the mis-registration due to terrain effect could be sufficiently reduced by the Gefolki algorithm.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.36T no.3
• /
• pp.32-40
• /
• 1999

In this paper, we present a fast block matching motion estimation algorithm based on successive elimination algorithm (SEA). Based on the characteristic of center-biased motion vector distribution in the search area, the proposed method improves the performance of the SEA with a reduced the number of the search positions in the search area, In addition, to reduce the computational load, this method is combined with both the reduced bits mean absolute difference (RBMAD) matching criterion which can be reduced the computation complexity of pixel comparison in the block matching and pixel decimation technique which reduce the number of pixels used in block matching. Simulation results show that the proposed method provides better performance than existing fast algorithms and similar to full-search block motion estimation algorithm.

• The KIPS Transactions:PartB
• /
• v.17B no.1
• /
• pp.63-68
• /
• 2010

In this paper, we propose a multiresolution stereo matching method based on genetic algorithm using edge information. The proposed approach considers the matching environment as an optimization problem and finds the solution by using a genetic algorithm. A cost function composes of certain constraints which are commonly used in stereo matching. We defines the structure of chromosomes using edge pixel information of reference image of stereo pair. To increase the efficiency of process, we apply image pyramid method to stereo matching and calculate the initial disparity map at the coarsest resolution. Then initial disparity map is propagated to the next finer resolution, interpolated and performed disparity refinement. We valid our approach not only reduce the search time for correspondence but alse ensure the validity of matching.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.3C
• /
• pp.258-263
• /
• 2006

Each pixel in a matching block does not equally contribute to block matching and the matching error is greatly affected by image complexity. On the basis of the facts, this paper proposes a fast motion estimation algorithm using some sub-blocks selected by the image complexity. The proposed algorithm divides a matching block into 16 sub-blocks, computes the image complexity in every sub-block, executes partial block matching using some sub-blocks with large complexity, and detects a motion vector. The simulation results show that the proposed algorithm brings about negligible image degradation, but can reduce a large amount of computation in comparison with conventional algorithms.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.393-396
• /
• 2000

본 논문에서는 영상의 화소값으로부터 추출된 유사 특징점(quasi-feature point)을 이용한 이미지 모자이킹 알고리즘을 제안한다. 유사 특징점의 선택은 전역 정합(global matching)의 결과로부터 중첩된 영역을 4개의 부영역(sub-area)으로 분할하고, 각각의 분할된 부 영역에서 국부 분산(local variance)의 크기가 큰 블록을 선정, 이 블록의 중심 화소를 유사 특징점으로 선택한다. 유사 특징점에 대한 정합은 카메라 이동에 따른 왜곡(distortion)과 조명의 변화를 고려한 블록 정합 알고리즘(block matching algorithm)을 이용한다.