• 융합신호처리학회논문지
• /
• 제19권4호
• /
• pp.199-205
• /
• 2018

기존의 전영역 탐색 방법의 많은 계산량으로 인하여 예측 화질 향상과 연산량 감축을 위한 연구가 진행되어 왔으며, 본 논문에서는 전영역 탐색기반의 방법과 비교하여 예측화질은 거의 유지하면서 효율적으로 계산량을 줄이는 방법을 제안한다. 제안하는 알고리즘은 다중 문턱치 필터를 이용하여 각 후보 지점에 대하여 부분 블록 에러 합을 계산하고, 이를 여러 문턱치 필터에 적용하여 각 후보들을 영역별로 분류 또는 제거하고, 이에 따라 다음 단계에서 진행할 후보들을 선별하고, 최소 에러지점의 최적후보에 대해 단계별 부동 회수를 비교 판단하여 그 다음 단계의 진행 여부를 결정함으로써 최적의 움직임 벡터를 고속으로 계산한다. 이를 통하여 전체의 최소블록매칭에러를 갖는 움직임 벡터를 조기에 발견하고, 불필요한 후보들을 더 빨리 제거함으로써 불필요한 계산량을 줄이고 계산속도 향상을 얻을 수 있다. 또한 제안하는 알고리즘은 단독으로 사용할 뿐만 아니라 기존의 고속 알고리즘들과 결합하여 사용해도 예측화질대비 우수한 연산량 감소를 얻을 수 있으며, 실험결과에서 이를 검증한다.

• 한국정보통신학회논문지
• /
• 제26권8호
• /
• pp.1130-1135
• /
• 2022

서울특별시는 25개 구청에 7만5천여대의 CCTV가 설치되어 있다. 각 구청은 CCTV관제를 위한 관제센터를 구축하고 시민의 안전을 위해 24시간 CCTV영상관제를 수행하고 있다. 서울특별시는 유관기관과 MOU를 체결하여 긴급/응급 상황에 신속한 대응이 가능하도록 구청의 CCTV영상을 제공하여 시민이 안전한 스마트시티통합플랫폼을 구축하고 있다. 본 논문에서는, 서울특별시 관할구청에서 사건 발생 시, CCTV영상에 대해 인공지능 DNN 기반의 Template Matching 기술, MLP 알고리즘과 CNN 기반으로 YOLO SPP DNN모델을 사용하여 사람과 차량을 판별하여 도주경로를 예측한다. 또한, 관할구청을 이탈하여, 차량 및 사람이 도주 시, 인접 구청에 영상정보와 상황정보를 자동전파 하도록 설계한다. 인공지능을 활용한 도주경로 예측 및 추적 시스템은 스마트시티 통합플랫폼을 전국으로 확장시킬 수 있다.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제10권3호
• /
• pp.273-281
• /
• 2004

동영상의 현재 블록의 움직임 벡터와 이전 블록의 움직임 벡터는 시간적 상관성을 갖고 있다. 본 논문에서는 영상의 시간적인 특성과 움직임 벡터의 가운데 중심 분포 특성을 이용하는 예측 탐색 알고리즘을 제안한다. 제안된 알고리즘은 이전 프레임 블록으로부터 예측된 움직임 벡터와 분할된 탐색 구간에 속하는 후보 벡터 중에서 가장 작은 SAD 값을 갖는 점을 정확한 움직임 벡터를 찾기 위한 초기 탐색점 위치로 결정한다. 실험 결과 제안된 방식은 FS를 제외한 기존의 대표적인 고속 탐색 방식들에 비해 PSNR 값에 있어서 평균적으로 0.19∼0.46㏈ 개선되고 영상에 따라 최고 1.06㏈ 정도 우수한 결과를 나타내었다.

• 전자공학회논문지S
• /
• 제34S권10호
• /
• 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.

• 대한의용생체공학회:의공학회지
• /
• 제23권2호
• /
• pp.101-107
• /
• 2002

이 논문에서는 자기공명심장영상에서 내벽과 외벽의 추출을 위한 반자동 분할 알고리즘을 제안하였다. 이 알고리즘은 Generalized gradient vector flow snake와 초기 윤곽선 예측 과정을 기반으로 한다. 특히 이 알고리즘은 내벽과 외벽의 공간적인 특설을 이용하며 Cross profile correlation matching (CPCM)을 사용한다. 현재 공간에서의 이전 시간에 관계된 영상과 현재 시간에서의 공간에 관계된 영상을 사용하여 초기 윤곽선 예측을 더욱 효과적으로 수행하였다. Multislice와 multiphase의 Siemens와 GE. Medinus 자기공명심장영상을 사용하여 실험하였고 많은 영상들에 대해 충분히 만족할만한 결과를 얻었다. 그리고 분할한 결과로 quantitative analysis를 수행하였고 시각적으로 보여주었다. 개발된 소프트웨어는 Visual C++을 사용하여 windows 환경의 응용프로그램으로 개발되었다.

• 제어로봇시스템학회논문지
• /
• 제12권10호
• /
• pp.1044-1049
• /
• 2006

Multiple sequence alignment is a method to compare two or more DNA or protein sequences. Most of multiple sequence alignment tools rely on pairwise alignment and Smith-Waterman algorithm to generate an alignment hierarchy. Therefore, in the existing multiple alignment method as the number of sequences increases, the runtime increases exponentially. In order to remedy this problem, we adopted a parallel processing suffix tree algorithm that is able to search for common subsequences at one time without pairwise alignment. Also, the cross-matching subsequences triggering inexact-matching among the searched common subsequences might be produced. So, the cross-matching masking process was suggested in this paper. To identify the function of the clusters generated by suffix tree clustering, BLAST and CDD (Conserved Domain Database)search were combined with a clustering tool. Our clustering and annotating tool consists of constructing suffix tree, overlapping common subsequences, clustering gene sequences and annotating gene clusters by BLAST and CDD search. The system was successfully evaluated with 36 gene sequences in the pentose phosphate pathway, clustering 10 clusters, finding out representative common subsequences, and finally identifying functional domains by searching CDD database.

• ETRI Journal
• /
• 제40권2호
• /
• pp.266-274
• /
• 2018

In error-prone wireless environments, it is difficult to realize video coding systems that are robust to various types of data loss. In this paper, a novel motion-vector refinement approach is presented for video error concealment. A traditional boundary-matching approach is exploited to reduce blocky effects along the block boundary. More specifically, a downhill simplex approach is combined with a boundary-matching approach to fine-tune the motion vectors, reducing the blocky effects along the prediction unit block boundary, and minimizing the computational cost. Extensive simulations are performed, and the results obtained verify the robustness and effectiveness of the proposed approach.

• 전자공학회논문지B
• /
• 제33B권6호
• /
• pp.64-72
• /
• 1996

In this paper, we propose predictive motion estimatin algorithm which can predict motion without additional side information considering spatio-tempral correlatio of motion vector. This method performs motion prediction of current block using correlation of the motion vector for two spatially adjacent blocks and a temporally adjacent block. Form predicted motion, the position of searhc area is determined. Then in this searhc area, we estimate motion vector of current block using block matching algoirthm. Considering spatial an temporal correlation of motion vector, the proposed method can predict motion precisely much more. Especially when the motion of objects is rapid, this method can estimate motion more precisely without reducing block size or increasing search area. Futhrmore, the proposed method has computation time the same as conventional block matching algorithm. And as it predicts motion from adjacent blocks, it does not require additional side information for adjacent block. Computer simulation results show that motion estimation of proposed method is more precise than that of conventioanl method.

• 오토저널
• /
• 제10권6호
• /
• pp.25-38
• /
• 1988

As a mean of increasing engine power, great attention has been concentrated on the turbo-charging owing to better fuel economy, smaller engine size and lower emission. The performance in turbocharged engine depends not only on the efficiency of the engine and the turbocharger used, but also on the total characteristics of the system by the matching turbocharger to the engine. The matching of the turbocharger to the engine has been usually accomplished by the empirical techniques with a great deal of laborious work. It would be better to predict the performance and emission in the turbocharged engine using the effective simulation model. In this study, computer simulation program has been developed to predict the transient variation of properties of gas in the cylinder, intake and exhaust pipes, the engine performances and emissions.

• Journal of Information Processing Systems
• /
• 제8권3호
• /
• pp.437-444
• /
• 2012

In this paper, we propose a method for predicting a user's location based on their past movement patterns. There is no restriction on the length of past movement patterns when using this method to predict the current location. For this purpose, a modified search tree has been devised. The search tree is constructed in an effective manner while it additionally learns the movement patterns of a user one by one. In fact, the time complexity of the learning process for a movement pattern is linear. In this process, the search tree expands to take into consideration more details about the movement patterns when a pattern that conflicts with an existing trained pattern is found. In this manner, the search tree is trained to make an exact matching, as needed, for location prediction. In the experiments, the results showed that this method is highly accurate in comparison with more complex and sophisticated methods. Also, the accuracy deviation of users of this method is significantly lower than for any other methods. This means that this method is highly stable for the variations of behavioral patterns as compared to any other method. Finally, 1.47 locations were considered on average for making a prediction with this method. This shows that the prediction process is very efficient.