• Review of KIISC
• /
• v.28 no.2
• /
• pp.33-42
• /
• 2018

머신러닝 및 인공지능 기술의 발전은 다양한 분야 활용되고 있고, 이는 보안 분야에서도 마찬가지로 로그 분석이나, 악성코드 탐지, 취약점 탐색 및 대응 등 다양한 분야에서 자동화를 위한 연구가 진행되고 있다. 특히 취약점 탐색 및 대응 분야의 경우 2016년 데프콘에서 진행된 CGC를 필두로 바이너리나 소스코드 내의 취약점을 정확하게 탐색하고 패치하기 위해 다양한 연구가 시도되고 있다. 이에 본 논문에서는 취약점을 탐색 및 대응하기 위해 각 연구 별 탐색 기술과 대응 기술을 분류 및 분석한다.

• Korean Journal of Remote Sensing
• /
• v.32 no.6
• /
• pp.647-656
• /
• 2016

Growth of UAV technology leads to expansion of UAV image applications. Many UAV image-based applications use a method called incremental bundle adjustment. However, incremental bundle adjustment produces large computation overhead because it attempts feature matching from all image pairs. For efficient feature matching process we have to confine matching only for overlapping pairs using exterior orientation parameters. When exterior orientation parameters are not available, we cannot determine overlapping pairs. We need another methods for feature matching candidate constitution. In this paper we compare matching candidate constitution methods without exterior orientation parameters, including partial feature matching, Bag-of-keypoints, image intensity method. We use the overlapping pair determination method based on exterior orientation parameter as reference. Experiment results showed the partial feature matching method in the one with best efficiency.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.4 s.316
• /
• pp.44-50
• /
• 2007

In this paper, we proposed the algorithm for the extraction of the corresponding points from images. The proposed algorithm EMSAC is based on RANSAC and EM algorithms. In the RANSAC procedure, the N corresponding points are randomly selected from the observed total corresponding points to estimate the homography matrix, H. This procedure continues on its repetition until the optimum H are estimated within number of repetition maximum. Therefore, it takes much time and does not converge sometimes. To overcome the drawbacks, the EM algorithm was used for the selection of N corresponding points. The EM algorithm extracts the corresponding points with the highest probability density to estimate the optimum H. By the experiments, it is demonstrated that the proposed method has exact and fast performance on extraction of corresponding points by combining RANSAC with EM.

• The Journal of the Korea Contents Association
• /
• v.12 no.6
• /
• pp.9-20
• /
• 2012

In computer vision, it is very important to obtain reliable corresponding feature points. However, we know it is not easy to find the corresponding feature points exactly considering by scaling, lighting, viewpoints, etc. Lots of SIFT methods applies the invariant to image scale and rotation and change in illumination, which is due to the feature vector extracted from corners or edges of object. However, SIFT could not find feature points, if edges do not exist in the area when we extract feature points along edges. In this paper, we present a new placement method of marker to improve the performance of SIFT feature detection and matching between different view of an object or scene. The shape of the markers used in the proposed method is formed in a semicircle to detect dominant direction vector by SIFT algorithm depending on direction placement of marker. We applied De Bruijn sequence for the markers direction placement to improve the matching performance. The experimental results show that the proposed method is more accurate and effective comparing to the current method.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.619-621
• /
• 1999

여러 대의 카메라를 통해 캡춰된 2차원 데이터를 사용하여 3차원의 좌표를 추출하기 위해서는 각 카메라의 2차원 영상 데이터들의 대응점(correpondence point)을 구해야 한다. 이를 위해 에피폴라 제약조건(epipolar constraints)을 이용하여 에피포라 라인(epipolar line)에 근접한 점을 추출할 수 있다. 에피폴라 제약조건을 사용하면, 실제 원하는 점 이외에 많은 수의 고스트(ghost)가 발생할 수 있다. 또한 카메라로부터 은닉(occlusion)된 점들로 인해 모든 카메라에서 대응되는 점이 존재하는지의 여부를 보장할 수 없다. 본 논문에서는 가 카메라의 대응관계를 k-partite graph로 모델링하고, 전역 탐색을 위해 가중치를 적용하여 클릭(clique)을 추출함으로서, 고스트가 제거된 대응점을 구한다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.6
• /
• pp.25-37
• /
• 2000

The trajectories of feature points can be defined by the correspondences between points in consecutive frames. The correspondence problem is known to be difficult to solve because false positives and false negatives almost always exist in real image sequences. In this paper, we propose a robust feature tracking algorithm considering incomplete trajectories such as entering and/or vanishing trajectories. The trajectories of feature points are determined by calculating the matching measure, which is defined as the minimum weighted Euclidean distance between two feature points. The weights are automatically updated in order to properly reflect the motion characteristics. We solve the correspondence problem as an optimal graph search problem, considering that the existence of false feature points may have serious effect on the correspondence search. The proposed algorithm finds a local optimal correspondence so that the effect of false feature point can be minimized in the decision process. The time complexity of the proposed graph search algorithm is given by O(mn) in the best case and O($m^2n$) in the worst case, where m and n arc the number of feature points in two consecutive frames. By considering false feature points and by properly reflecting motion characteristics, the proposed algorithm can find trajectories correctly and robustly, which has been shown by experimental results.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.553-555
• /
• 2000

인체와 같은 다관절체의 운동은 세그먼트 단위로 강체의 특성을 포함하고 있으나, 움직임에 따라 옷의 주름과 같은 잡음과 관절의 변화 등의 비강체의 성질을 가진다. 따라서 잡음과 움직임에 따라 다양한 특징점이 추출되며, 영상 간 특징점의 변화가 심하므로, 대상의 특징을 비교적 정확히 반영하는 대응관계를 가진 특징점을 추출하는 것은 어려운 문제이다. 본 논문에서는 인체와 같은 다관절체의 움직임으로부터 신뢰성 있는 대응관계를 가진 특징점을 추출하기 위한 기법을 제안한다. 또한 쌍 대응(pairwise correspondence)의 문제를 확장하여 특정 동작을 이루는 다수의 프레임에서의 일관성 있는 특징점 대응을 위한 간단한 전략을 제안한다. 이를 통해 정확하고 안정적인 대응관계를 가진 특징점을 추출할 수 있다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.144-159
• /
• 2014

Techniques for making a single panoramic image using multiple pictures are widely studied in many areas such as computer vision, computer graphics, etc. The panorama image can be applied to various fields like virtual reality, robot vision areas which require wide-angled shots as an useful way to overcome the limitations such as picture-angle, resolutions, and internal informations of an image taken from a single camera. It is so much meaningful in a point that a panoramic image usually provides better immersion feeling than a plain image. Although there are many ways to build a panoramic image, most of them are using the way of extracting feature points and matching points of each images for making a single panoramic image. In addition, those methods use the RANSAC(RANdom SAmple Consensus) algorithm with matching points and the Homography matrix to transform the image. The SURF(Speeded Up Robust Features) algorithm which is used in this paper to extract featuring points uses an image's black and white informations and local spatial informations. The SURF is widely being used since it is very much robust at detecting image's size, view-point changes, and additionally, faster than the SIFT(Scale Invariant Features Transform) algorithm. The SURF has a shortcoming of making an error which results in decreasing the RANSAC algorithm's performance speed when extracting image's feature points. As a result, this may increase the CPU usage occupation rate. The error of detecting matching points may role as a critical reason for disqualifying panoramic image's accuracy and lucidity. In this paper, in order to minimize errors of extracting matching points, we used $3{\times}3$ region's RGB pixel values around the matching points' coordinates to perform intermediate filtering process for removing wrong matching points. We have also presented analysis and evaluation results relating to enhanced working speed for producing a panorama image, CPU usage rate, extracted matching points' decreasing rate and accuracy.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.24-32
• /
• 2006

본 논문에서는 다시점 카메라부터 획득된 부분적인 3D 점군을 사용하여 실내환경의 3D 복원을 위한 새로운 방법을 제안한다. 지금까지 다양한 양안차 추정 알고리즘이 제안되었으며, 이는 활용 가능한 깊이 영상이 다양함을 의미한다. 따라서, 본 논문에서는 일반화된 다시점 카메라를 이용하여 실내환경을 복원하는 방법을 다룬다. 첫 번째, 3D 점군들의 시간적 특성을 기반으로 변화량이 큰 3D 점들을 제거하고, 공간적 특성을 기반으로 주변의 3D 점을 참조하여 빈 영역을 채움으로써 깊이 영상 정제 과정을 수행한다. 두 번째, 연속된 두 시점에서의 3D 점군을 동일한 영상 평면으로 투영하고, 수정된 KLT (Kanade-Lucas-Tomasi) 특징 추적기를 사용하여 대응점을 찾는다. 그리고 대응점 간의 거리 오차를 최소화함으로써 정밀한 정합을 수행한다. 마지막으로, 여러 시점에서 획득된 3D 점군과 한 쌍의 2D 영상을 동시에 이용하여 3D 점들의 위치를 세밀하게 조절함으로써 최종적인 3D 모델을 생성한다. 제안된 방법은 대응점을 2D 영상 평면에서 찾음으로써 계산의 복잡도를 줄였으며, 3D 데이터의 정밀도가 낮은 경우에도 효과적으로 동작한다. 또한, 다시점 카메라를 이용함으로써 수 시점에서의 깊이 영상과 컬러 영상만으로도 실내환경 3D 복원이 가능하다. 제안된 방법은 네비게이션 뿐만 아니라 상호작용을 위한 3D 모델 생성에 활용될 수 있다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.6
• /
• pp.505-510
• /
• 2016

This paper presents a searching method of corresponding points robust to rotational error for scan-matching used for SLAM(Simultaneous Localization and Mapping) in mobile robot. A differential driving mechanism is one of the most popular type for mobile robot. For driving curved path, this type controls the velocities of each two wheels independently. This case increases a wheel slip of the mobile robot more than the case of straight path driving. And this is the reason of a drifting problem. To handle this problem and improves the performance of scan-matching, this paper proposes a searching method of corresponding points using extraction of a closest point based on rotational radius of the mobile robot. To verify the proposed method, the experiment was conducted using LRF(Laser Range Finder). Then the proposed method is compared with an existing method, which is an existing method based on euclidian closest point. The result of our study reflects that the proposed method can improve the performance of searching corresponding points.