• 한국정밀공학회지
• /
• 제30권6호
• /
• pp.601-606
• /
• 2013

3D scanning is a technique to measure the 3D shape information of the object. Shape information obtained by 3D scanning is expressed either as point cloud or as polygon mesh type data that can be widely used in various areas such as reverse engineering and quality inspection. 3D scanning should be performed as accurate as possible since the scanned data is highly required to detect the features on an object in order to scan the shape of the object more precisely. In this study, we propose the method on finding the location of feature more accurately, based on the extended Biplane SNAKE with global optimization. In each iteration, we project the feature lines obtained by the extended Biplane SNAKE into each image plane and move the feature lines to the features on each image. We have applied this approach to real models to verify the proposed optimization algorithm.

• 전기학회논문지
• /
• 제68권1호
• /
• pp.182-188
• /
• 2019

Autonomous mobile robots need SLAM (simultaneous localization and mapping) to look for the location and simultaneously to make the map around the location. In order to achieve visual SLAM, it is necessary to form an algorithm that detects and extracts feature points from camera images, and gets the camera pose and 3D points of the features. In this paper, we propose MPROSAC algorithm which combines MSAC and PROSAC, and compare the performance of optimization method and the filtering method for feature-based monocular visual SLAM. Sparse Bundle Adjustment (SBA) is used for the optimization method and the extended Kalman filter is used for the filtering method.

• 제어로봇시스템학회논문지
• /
• 제21권4호
• /
• pp.367-371
• /
• 2015

In this paper, a novel localization method for a monocular camera is proposed by using a feature-based probabilistic map. The localization of a camera is generally estimated from 3D-to-2D correspondences between a 3D map and an image plane through the PnP algorithm. In the computer vision communities, an accurate 3D map is generated by optimization using a large number of image dataset for camera pose estimation. In robotics communities, a camera pose is estimated by probabilistic approaches with lack of feature. Thus, it needs an extra system because the camera system cannot estimate a full state of the robot pose. Therefore, we propose an accurate localization method for a monocular camera using a probabilistic approach in the case of an insufficient image dataset without any extra system. In our system, features from a probabilistic map are projected into an image plane using linear approximation. By minimizing Mahalanobis distance between the projected features from the probabilistic map and extracted features from a query image, the accurate pose of the monocular camera is estimated from an initial pose obtained by the PnP algorithm. The proposed algorithm is demonstrated through simulations in a 3D space.

• 전자공학회논문지B
• /
• 제33B권5호
• /
• pp.60-72
• /
• 1996

In this paper, a enw model-base three-dimensional (3-D) object recognition mehtod using hopfield network is proposed. To minimize deformation of feature values on 3-D rotation, we select 3-D shape features and 3-D relational features which have rotational invariant characteristics. Then these feature values are normalized to have scale invariant characteristics, also. The input features are matched with model features by optimization process of hopjfield network in the form of two dimensional arrayed neurons. Experimental results on object classification and object matching with the 3-D rotated, scale changed, an dpartial oculued objects show good performance of proposed method.

• 한국정보전자통신기술학회논문지
• /
• 제16권6호
• /
• pp.499-508
• /
• 2023

본 논문에서는 3차원 공간 내에서 동일 평면 상에 존재하는 특징점들의 좌표를 추정하기 위한 기법을 제안한다. 제안된 방법은 카메라 영상만을 이용하여 3차원 공간 내에 존재하는 다수의 특징점들을 검출한 다음 동일 평면 상에 위치하지 않는 특징점들은 제거시킨다. 이를 위해서 3차원 공간 내의 평면 객체와 2차원 카메라 영상 평면 사이의 평면 호모그래피(homography) 관계를 추정한 다음 각 특징점들의 평면 객체 상에서의 역사영 오차를 계산하고 오차값이 기준 값보다 큰 특징점들은 좌표값 추정 과정에서 제외시킨다. 제안된 방법은 별도의 센서 또는 최적화 알고리즘 없이 카메라 영상으로부터 추정된 평면 호모그래피 만을 이용한다. 실험 결과를 통해서 초당 40프레임 이상의 처리 속도를 보인다는 것을 확인할 수 있었으며, 또한 RGB-D 카메라를 이용하는 경우와 비교해도 처리 속도에 큰 차이를 보이지 않았으며, 특히 제안된 방법은 검출되는 특징점의 수가 지속적으로 증가하는 조건에서도 처리 속도가 거의 영향을 받지 않음을 알 수 있었다.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2003년도 추계학술대회 및 정기총회
• /
• pp.201-206
• /
• 2003

In clinical practice, CT Angiography is a powerful technique for the visualziation of blood flow in arterial vessels throughout the body. However CT Angiography images of blood vessels anywhere in the body may be fuzzy if the patient moves during the exam. In this paper, we propose a novel technique for removing global motion artifacts in the 3D space. The proposed methods are based on the two key ideas as follows. First, the method involves the extraction of a set of feature points by using a 3D edge detection technique based on image gradient of the mask volume where enhanced vessels cannot be expected to appear, Second, the corresponding set of feature points in the contrast volume are determined by correlation-based registration. The proposed method has been successfully applied to pre- and post-contrast CTA brain dataset. Since the registration for motion correction estimates correlation between feature points extracted from skull area in mask and contrast volume, it offers an accelerated technique to accurately visualize blood vessels of the brain.

• 전자공학회논문지C
• /
• 제35C권2호
• /
• pp.71-79
• /
• 1998

In this paper, we propose a new mART(modified ART) neural network by combining the winner neuron definition method of SOM(self-organizing map) and the real-time adaptive clustering function of ART(adaptive resonance theory) and construct it in a modular structure, for the purpose of organizing the feature maps of three dimensional targets. Being constructed in a modular structure, the proposed modular mART can effectively prevent the clusters from representing multiple classes and can be trained to organze two dimensional distortion invariant feature maps so as to recognize targets with three dimensional distortion. We also present the recognition result and self-organization perfdormance of the proposed modular mART neural network after carried out some experiments with 14 tank and fighter target models.

• 한국컴퓨터정보학회논문지
• /
• 제24권2호
• /
• pp.119-126
• /
• 2019

As interest in augmented reality has increased recently, attempts have been made to incorporate augmented reality into various fields. In implementing augmented reality, the method by which markers are used is to extract feature points of markers to recognize 3D coordinates and, in some cases, it is necessary to recognize multiple markers simultaneously. Therefore, this paper proposes optimization methods for recognising multiple markers at the same time. Unity 3D and augmented reality library Vuforia are used to implement the experimental environment. The augmented reality program produced was implemented in an application form and tested using a mobile camera. We looked for optimization methods for manufacturing markers directly and for recognizing multiple markers through changes in the experimental environment. The results of the experiment can provide a higher recognition rate in an environment where multiple marker recognition is required later.

• 방송공학회논문지
• /
• 제26권3호
• /
• pp.247-257
• /
• 2021

본 논문에서는 3D(dimensional) 스켈레톤을 이용하여 다시점 RGB-D 카메라를 캘리브레이션 하는 새로운 기법을 제안하고자 한다. 다시점 카메라를 캘리브레이션 하기 위해서는 일관성 있는 특징점이 필요하다. 또한 높은 정확도의 캘리브레이션 결과를 얻기 위해서는 정확한 특징점의 획득이 필요하다. 우리는 다시점 카메라를 캘리브레이션 하기 위한 특징점으로 사람의 스켈레톤을 사용한다. 사람의 스켈레톤은 최신의 자세 추정(pose estimation) 알고리즘들을 이용하여 쉽게 구할 수 있게 되었다. 우리는 자세 추정 알고리즘을 통해서 획득된 3D 스켈레톤의 관절 좌표를 특징점으로 사용하는 RGB-D 기반의 캘리브레이션 알고리즘을 제안한다. 다시점 카메라에 촬영된 인체 정보는 불완전할 수 있기 때문에, 이를 통해 획득된 영상 정보를 바탕으로 예측된 스켈레톤은 불완전할 수 있다. 불완전한 다수의 스켈레톤을 효율적으로 하나의 스켈레톤으로 통합한 후에, 통합된 스켈레톤을 이용하여 카메라 변환 행렬을 구함으로써 다시점 카메라들을 캘리브레이션 할 수 있다. 캘리브레이션의 정확도를 높이기 위해서 시간적인 반복을 통해서 다수의 스켈레톤을 최적화에 이용한다. 우리는 실험을 통해서 불완전한 다수의 스켈레톤을 이용하여 다시점 카메라를 캘리브레이션 할 수 있음을 증명한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권8호
• /
• pp.3136-3150
• /
• 2015

A vision-based 3D tracking of articulated human hand is one of the major issues in the applications of human computer interactions and understanding the control of robot hand. This paper presents an improved approach for tracking and recovering the 3D position and orientation of a human hand using the Kinect sensor. The basic idea of the proposed method is to solve an optimization problem that minimizes the discrepancy in 3D shape between an actual hand observed by Kinect and a hypothesized 3D hand model. Since each of the 3D hand pose has 23 degrees of freedom, the hand articulation tracking needs computational excessive burden in minimizing the 3D shape discrepancy between an observed hand and a 3D hand model. For this, we first created a 3D hand model which represents the hand with 17 different parts. Secondly, Random Forest classifier was trained on the synthetic depth images generated by animating the developed 3D hand model, which was then used for Haar-like feature-based classification rather than performing per-pixel classification. Classification results were used for estimating the joint positions for the hand skeleton. Through the experiment, we were able to prove that the proposed method showed improvement rates in hand part recognition and a performance of 20-30 fps. The results confirmed its practical use in classifying hand area and successfully tracked and recovered the 3D hand pose in a real time fashion.