• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.919-927
• /
• 2019

In this paper, we propose an accurate camera calibration method for acquiring multiview stereoscopic images. Generally, camera calibration is performed by using checkerboard structured patterns. The checkerboard pattern simplifies feature point extraction process and utilizes previously recognized lattice structure, which results in the accurate estimation of relations between the point on 2-dimensional image and the point on 3-dimensional space. Since estimation accuracy of camera parameters is dependent on feature matching, accurate detection of checkerboard corner is crucial. Therefore, in this paper, we propose the method that performs accurate camera calibration method through accurate detection of checkerboard corners. Proposed method detects checkerboard corner candidates by utilizing 1-dimensional gaussian filters with succeeding corner refinement process to remove outliers from corner candidates and accurately detect checkerboard corners in sub-pixel unit. In order to verify the proposed method, we check reprojection errors and camera location estimation results to confirm camera intrinsic parameters and extrinsic parameters estimation accuracy.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.3
• /
• pp.197-205
• /
• 1992

In this paper object recognition using neural network is studied. The recognition is accomplished by matching linear line segments which are formed by local features extracted from the curvature points. Since there is similarities among segments. The boundary of models is not distinct in feature space. Due to these indistinctness the ambiguity of recognition occurs, and the recognition rate becomes degraded according to the limitation of boundary decision capability of neural network for similar of features. Object recognition and to improve recognition rate. Local features are used to represent the object effectively. The validity of the object recognition system is demonstrated by experiments for the occluded and varied objects.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.3
• /
• pp.535-541
• /
• 2006

This paper proposes a robust method to find corresponding points for un-calibrated stereo images by using a classical method based on the epipolar constraints and motion flows. If we detect matching for the only epipolar geometry, the problem is very high. Therefore, in order to nod an initial set of matches, we use the correlation technique and then exploit motion vectors to remove mismatches among matching candidates. Then, the epipolar geometry can be accurately estimated using a veil adapted criterion and computed the fundamental matrix. The proposed algorithm has been widely tested and works remarkably well in various scenes, evenly, with many repetitive patterns. The results show that the proposed algorithm is better than the conventional.

• The KIPS Transactions:PartB
• /
• v.17B no.5
• /
• pp.355-362
• /
• 2010

Face tracking is to estimate the motion of a non-rigid face together with a rigid head in 3D, and plays important roles in higher levels such as face/facial expression/emotion recognition. In this paper, we propose an AAM-based face tracking algorithm. AAM has been widely used to segment and track deformable objects, but there are still many difficulties. Particularly, it often tends to diverge or converge into local minima when a target object is self-occluded, partially or completely occluded. To address this problem, we utilize the scale invariant feature transform (SIFT). SIFT is an effective method for self and partial occlusion because it is able to find correspondence between feature points under partial loss. And it enables an AAM to continue to track without re-initialization in complete occlusions thanks to the good performance of global matching. We also register and use the SIFT features extracted from multi-view face images during tracking to effectively track a face across large pose changes. Our proposed algorithm is validated by comparing other algorithms under the above 3 kinds of occlusions.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.25-28
• /
• 2016

본 논문에서는 실시간 얼굴 추적을 위하여 기존의 CamShift 알고리즘의 단점을 보완한 새로운 CamShift 알고리즘을 제안한다. 배경 내 추적 객체와 색상이 유사한 객체가 존재할 경우 기존 CamShift 알고리즘은 불안정한 추적을 보여준다. 이러한 문제점을 화소 단위로 거리정보를 획득할 수 있는 Kinect 의 깊이 정보와 HSV 색공간 기반의 피부색 후보영역을 추출하는 Skin Detection 알고리즘을 이용하여 색상분포만 이용하는 기존의 CamShift 의 단점을 보완한다. 또한 추적하던 객체가 사라지거나 가려짐이 발생할 경우에도 다시 추적할 수 있는 특징점 기반의 매칭 알고리즘을 통하여 차폐영역에 강인한 특성을 가지게 한다. 이러한 향상된 CamShift 알고리즘을 사람의 얼굴 추적에 적용함으로써 다양한 분야에 활용 가능한 강인한 얼굴추적 알고리즘을 제안하고자 한다. 실험결과 제안하는 알고리즘은 기존의 추적 알고리즘인 TLD 보다 월등히 빠른 처리속도와 더 우수한 추적성능을 보여주었고, CamShift 보다 조금 느리지만 기존의 CamShift 가 가지고 있는 문제점들을 해결하였다.

• The Journal of Korea Robotics Society
• /
• v.15 no.1
• /
• pp.1-7
• /
• 2020

In this paper, we introduce the methodology that utilizes deep learning-based front-end to enhance underwater feature matching. Both optical camera and sonar are widely applicable sensors in underwater research, however, each sensor has its own weaknesses, such as light condition and turbidity for the optic camera, and noise for sonar. To overcome the problems, we proposed the opti-acoustic transformation method. Since feature detection in sonar image is challenging, we converted the sonar image to an optic style image. Maintaining the main contents in the sonar image, CNN-based style transfer method changed the style of the image that facilitates feature detection. Finally, we verified our result using cosine similarity comparison and feature matching against the original optic image.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.11a
• /
• pp.136-138
• /
• 2017

본 논문에서는 동적 프로그래밍 스티칭을 이용하여 다수의 이미지를 경계가 보이지 않게 정합하여 고해상도의 이미지를 얻는 방법을 소개한다. 제안하는 방법에서는 수직, 수평방향으로 일정한 간격으로 쵤영한 다수의 지역 이미지와 전체를 촬영한 전역 이미지를 사용해서 각각의 지역 이미지와 전역 이미지의 특징점을 추출하고 이를 매칭하여 호모그래피를 계산한다. 이를 이용하여 정합할 두 지역 이미지간의 호모그래피를 구하고 좌표를 변환한 후 겹치는 영역에 동적 프로그래밍 스티칭 방법을 적용하여 두 이미지를 정합한다. 동적 프로그래밍 스티칭 방법이란 두 이미지를 정합할 때 겹치는 영역의 차이를 계산하고 차이가 가장 적은 픽셀을 경계로 하는 방법이다. 다수의 이미지를 수직방향으로 정합하고 정합된 이미지들을 수평방향으로 정합하여 하나의 고해상도 이미지를 만들 수 있다. 제안하는 스티칭 기법을 적용함으로써 이미지간의 경계가 드러나지 않을 뿐만 아니라 각 픽셀의 세밀한 정보도 유지한 고해상도의 이미지를 획득할 수 있음을 보였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.01a
• /
• pp.35-36
• /
• 2017

실시간 객체 인식은 카메라로부터 입력받은 영상 내에 존재하는 객체를 실시간으로 처리하는 기술로써 정확한 인식률과 빠른 인식 속도를 가져야 한다. 하지만 인식 속도가 보장되지 않으면 실시간으로 객체를 인식 할 수 없고 인식률이 보장되지 않으면 객체 인식을 통해 구현한 기능이 올바르게 동작하지 않을 수 도 있다. 따라서 본 논문에서는 실시간으로 객체를 인식하는 기술을 분류하고 연구 동향을 소개한다. 그리고 실시간 객체 인식을 위한 향후 연구 방향을 제시한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.6
• /
• pp.759-764
• /
• 2005

In this paper we describe a face recognition using EBGM(Elastic Bunch Graph Matching) method. Usally, the PCA and LDA based face recognition method with the low-dimensional subspace representation use holistic image of faces, but this study uses local features such as a set of convolution coefficients for Gabor kernels of different orientations and frequencies at fiducial points including the eyes, nose and mouth. At pre-recognition step, all images are represented with same size face graphs and they are used to recognize a face comparing with each similarity for all images. The proposed algorithm has less computation time due to simplified face graph than conventional EBGM method and the fuzzy matching method for calculating the similarity of face graphs renders more face recognition results.

• The Journal of the Korea Contents Association
• /
• v.8 no.1
• /
• pp.212-227
• /
• 2008

Since 3D face can be rotated freely in 3D space and illumination effects can be modeled properly, 3D face modeling Is more precise and realistic in face pose, illumination, and expression than 2D face modeling. Thus, 3D modeling is necessitated much in face recognition, game, avatar, and etc. In this paper, we propose a 3D face modeling method based on 3D morphable shape modeling. The proposed 3D modeling method first constructs a 3D morphable shape model out of 3D face scan data obtained using a 3D scanner Next, the proposed method extracts and matches feature points of the face from 2D image sequence containing a face to be modeled, and then estimates 3D vertex coordinates of the feature points using a factorization based SfM technique. Then, the proposed method obtains a 3D shape model of the face to be modeled by fitting the 3D vertices to the constructed 3D morphable shape model. Also, the proposed method makes a cylindrical texture map using 2D face image sequence. Finally, the proposed method builds a 3D face model by rendering the 3D face shape model with the cylindrical texture map. Through building processes of 3D face model by the proposed method, it is shown that the proposed method is relatively easy, fast and precise than the previous 3D face model methods.