• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.877-880
• /
• 2000

In this paper, we develop an algorithm of soccer image sequences mosaicing using reverse affine transform. The continuous mosaic images of soccer ground field allows the user/viewer to view a “wide picture” of the player’s actions The first step of our algorithm is to automatic detection and tracking player, ball and some lines such as center circle, sideline, penalty line and so on. For this purpose, we use the ground field extraction algorithm using color information and player and line detection algorithm using four P-rules and two L-rules. The second step is Affine transform to map the points from image to model coordinate using predefined and pre-detected four points. General Affine transformation has many holes in target image. In order to delete these holes, we use reverse Affine transform. We tested our method in real image sequence and the experimental results are given.

• Journal of Information Processing Systems
• /
• 제11권4호
• /
• pp.643-654
• /
• 2015

Face recognition under controlled settings, such as limited viewpoint and illumination change, can achieve good performance nowadays. However, real world application for face recognition is still challenging. In this paper, we propose using the combination of Affine Scale Invariant Feature Transform (SIFT) and Probabilistic Similarity for face recognition under a large viewpoint change. Affine SIFT is an extension of SIFT algorithm to detect affine invariant local descriptors. Affine SIFT generates a series of different viewpoints using affine transformation. In this way, it allows for a viewpoint difference between the gallery face and probe face. However, the human face is not planar as it contains significant 3D depth. Affine SIFT does not work well for significant change in pose. To complement this, we combined it with probabilistic similarity, which gets the log likelihood between the probe and gallery face based on sum of squared difference (SSD) distribution in an offline learning process. Our experiment results show that our framework achieves impressive better recognition accuracy than other algorithms compared on the FERET database.

• 한국통신학회논문지
• /
• 제33권9C호
• /
• pp.712-719
• /
• 2008

시간적 에러은닉 기법은 손실된 데이터를 포함한 프레임과 이전프레임사이의 시간적 상관도(temporal correlation)를 이용하여 손실된 데이터를 복원하는 기술을 말한다. 이러한 시간적 에러은닉 방법은 블록단위의 복원기술과 화소단위의 복원기술로 나눌 수 있다. 본 논문에서 제안하는 방법은 어파인변환(affine transform)을 이용한 화소단위의 시간적 에러은닉에 관한 것으로 이는 손실된 블록내에 객체 또는 배경이 어파인 모델로 모델링 될 수 있는 기하학적 변환 즉 회전, 확대, 축소와 같은 변환이 있는 경우 더욱 높은 성능을 가진다. 또한 어파인 모델의 계산과정에 사용되는 움직임벡터가 서로 다른 객체의 움직임을 나타내는 경우에도 높은 성능을 유지하기 위해 비용함수를 정의하고 비용 값에 따라 적응적으로 어파인 에러은닉방법을 적용함으로써 보다 높은 성능을 가지게 한다. 실험결과 제안하는 알고리즘은 현재 H.264/AVC 참조소프트웨어에서 방법과 비교하여 최대 1.9 dB까지의 객관적 화질향상이 있는 것으로 나타난다.

• 전자공학회논문지S
• /
• 제36S권1호
• /
• pp.60-69
• /
• 1999

초저속 동영상 부호화에서 블록화 현상을 해결하기 위해 affine 변환을 이용한 움직임 보상 방법이 제안되었고 움직임 추정에서 정밀한 움직임 추정하기 위해 육각형 정합 알고리듬이 제안되었다. Affine 변환에서 영상을 삼각형 조각들로 나눌 때 삼각형 형태와 물체가 불일치할수록 보상 영상의 예측 에러가 증가하고 일그러짐 현상이 나타난다. 본 논문에서는 이러한 문제점을 해결하기 위해 영상의 윤곽 정보에 따라 다른 형태의 삼각형 조각들로 나누고, 또한 윤곽 정보가 복잡한 부분은 삼각형을 세분화하는 알고리듬을 제안한다. 제안한 방법에서 정밀한 움직밍 벡터를 추정할 때 이웃하는 삼각형 조각 형태 차이로 인하여 다각형 정합 알고리듬을 제안하고 H.263과 성능르 비교한다.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제18권2호
• /
• pp.181-192
• /
• 2014

In this paper, we propose a robust real-time myocardial border tracking algorithm for echocardiography. Commonly, after an initial contour of LV border is traced at one or two frame from the entire cardiac cycle, LV contour tracking is performed over the remaining frames. Among a variety of tracking techniques, optical flow method is the most widely used for motion estimation of moving objects. However, when echocardiography data is heavily corrupted in some local regions, the errors bring the tracking point out of the endocardial border, resulting in distorted LV contours. This shape distortion often occurs in practice since the data acquisition is affected by ultrasound artifacts, dropout or shadowing phenomena of cardiac walls. The proposed method deals with this shape distortion problem and reflects the motion realistic LV shape by applying global deformation modeled as affine transform partitively to the contour. We partition the tracking points on the contour into a few groups and determine each affine transform governing the motion of the partitioned contour points. To compute the coefficients of each affine transform, we use the least squares method with equality constraints that are given by the relationship between the coefficients and a few contour points showing good tracking results. Many real experiments show that the proposed method supports better performance than existing methods.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(4)
• /
• pp.35-38
• /
• 2000

The method of Content-based Triangular Mesh Image representation in moving pictures makes better performance in prediction error ratio and visual efficiency than that of classical block matching. Specially if background and objects can be separated from image, the objects are designed by Irregular mesh. In this case this irregular mesh design has an advantage of increasing video coding efficiency. This paper presents the techniques of mesh generation, motion estimation using these mesh, uses image warping transform such as Affine transform for image reconstruction, and evaluates the content based mesh design through computer simulation.

• 한국컴퓨터정보학회논문지
• /
• 제4권2호
• /
• pp.135-140
• /
• 1999

본 논문은 영상 부호화시에 걸리는 오랜 시간을 줄이기 위해 스케일링 방식과 탐색영역 제한방식을 이용한 어핀변환 부호화 방식을 제안한다. 제안한 방법의 성능을 평가하기 위해, 제안한 알고리즘과 전통적인 어핀변환 부호화 방식을 사용하는 Jacquin의 방법과 비교하였다. 시뮬레이션 결과, 제안한 알고리즘은 스케일링 방식과 탐색영역 제한 방식을 사용하므로써, 부호화 시간을 상당히 줄일 수 있었다. Jacquin의 방식과 비교해, 복원된 영상의 화질은 약간 저하되었지만 부호화 시간을 많이 단축하였다.

• International Journal of Contents
• /
• 제9권2호
• /
• pp.1-7
• /
• 2013

This paper proposes an efficient matching algorithm based on ASIFT (Affine Scale-Invariant Feature Transform) which is fully invariant to affine transformation. In our approach, we proposed a method of reducing similar measure matching cost and the number of outliers. First, we combined the Manhattan and Chessboard metrics replacing the Euclidean metric by a linear combination for measuring the similarity of keypoints. These two metrics are simple but really efficient. Using our method the computation time for matching step was saved and also the number of correct matches was increased. By applying an Optimized Random Sampling Algorithm (ORSA), we can remove most of the outlier matches to make the result meaningful. This method was experimented on various combinations of affine transform. The experimental result shows that our method is superior to SIFT and ASIFT.

• IEIE Transactions on Smart Processing and Computing
• /
• 제1권2호
• /
• pp.78-87
• /
• 2012

In this paper, we address the tracking problem caused by camera motion and rolling shutter effects associated with CMOS sensors in consumer handheld cameras, such as mobile cameras, digital cameras, and digital camcorders. A modified particle filtering method is proposed for simultaneously tracking objects and compensating for the effects of camera motion. The proposed method uses an elastic registration algorithm (ER) that considers the global affine motion as well as the brightness and contrast between images, assuming that camera motion results in an affine transform of the image between two successive frames. By assuming that the camera motion is modeled globally by an affine transform, only the global affine model instead of the local model was considered. Only the brightness parameter was used in intensity variation. The contrast parameters used in the original ER algorithm were ignored because the change in illumination is small enough between temporally adjacent frames. The proposed particle filtering consists of the following four steps: (i) prediction step, (ii) compensating prediction state error based on camera motion estimation, (iii) update step and (iv) re-sampling step. A larger number of particles are needed when camera motion generates a prediction state error of an object at the prediction step. The proposed method robustly tracks the object of interest by compensating for the prediction state error using the affine motion model estimated from ER. Experimental results show that the proposed method outperforms the conventional particle filter, and can track moving objects robustly in consumer handheld imaging devices.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2014년도 춘계학술발표대회
• /
• pp.781-784
• /
• 2014

Face recognition under controlled settings, such as limited viewpoint and illumination change, can achieve good performance nowadays. However, real world application for face recognition is still challenging. In this paper, we use Affine SIFT to detect affine invariant local descriptors for face recognition under large viewpoint change. Affine SIFT is an extension of SIFT algorithm. SIFT algorithm is scale and rotation invariant, which is powerful for small viewpoint changes in face recognition, but it fails when large viewpoint change exists. In our scheme, Affine SIFT is used for both gallery face and probe face, which generates a series of different viewpoints using affine transformation. Therefore, Affine SIFT allows viewpoint difference between gallery face and probe face. Experiment results show our framework achieves better recognition accuracy than SIFT algorithm on FERET database.