• Journal of Electrical Engineering and Technology
• /
• 제11권6호
• /
• pp.1846-1856
• /
• 2016

This study proposes a novel feature point initialization method in order to improve the accuracy of feature point positions by fusing a vision sensor and a lidar. The initialization is a process that determines three dimensional positions of feature points through two dimensional image data, which has a direct influence on performance of a 6-DoF bearing-only SLAM. Prior to the initialization, an extrinsic calibration method which estimates rotational and translational relationships between a vision sensor and lidar using multiple calibration tools was employed, then the feature point initialization method based on the estimated extrinsic calibration parameters was presented. In this process, in order to improve performance of the accuracy of the initialized feature points, an iterative automatic scaling parameter tuning technique was presented. The validity of the proposed feature point initialization method was verified in a 6-DoF bearing-only SLAM framework through an indoor and outdoor tests that compare estimation performance with the previous initialization method.

• 제어로봇시스템학회논문지
• /
• 제22권10호
• /
• pp.833-838
• /
• 2016

This paper presents a performance evaluation of various feature-initialization algorithms for forward-viewing mono-camera based simultaneous localization and mapping (SLAM), specifically in indoor environments. For mono-camera based SLAM, the position of feature points cannot be known from a single view; therefore, it should be estimated from a feature initialization method using multiple viewpoint measurements. The accuracy of the feature initialization method directly affects the accuracy of the SLAM system. In this study, four different feature initialization algorithms are evaluated in simulations, including linear triangulation; depth parameterized, linear triangulation; weighted nearest point triangulation; and particle filter based depth estimation algorithms. In the simulation, the virtual feature positions are estimated when the virtual robot, containing a virtual forward-viewing mono-camera, moves forward. The results show that the linear triangulation method provides the best results in terms of feature-position estimation accuracy and computational speed.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권6호
• /
• pp.784-791
• /
• 2004

본 논문에서는 퍼지논리에 기초한 Fisherface 얼굴인식 방법의 확장을 다룬다. Fisherface 얼굴인식 방법은 주성분 분석 기법만을 이용하는 경우에 비해 조명의 방향, 얼굴의 포즈, 감정과 같은 변동에 대해 민감하지 않은 장점을 가지고 있다. 그러나, Fisherface 방법을 포함한 얼굴인식의 다양한 방법들은 입력 벡터가 한 클래스에 할당되어질 때 그 클래스에서 소속의 정도를 0 또는 1로서 나타낸다. 따라서 이러한 방법들은 얼굴영상들이 조명이나 보는 각도로 인해 변형이 생기는 경우에 인식률이 저하되는 문제가 있다. 본 논문에서는 PCA에 의해 변환된 특징벡터에 퍼지 소속도를 할당하는 것으로, 퍼지 소속도는 퍼지 kNN(k-Nearest Neighbor)으로부터 얻어진다. 실험 결과 ORL, Yale 얼굴 데이타베이스에서 기존의 인식방법 보다 향상된 인식 성능을 보임을 알 수 있었다.

• 대한의용생체공학회:의공학회지
• /
• 제26권6호
• /
• pp.357-363
• /
• 2005

Active contour models have been extensively used to segment, match, and track objects of interest in computer vision and image processing applications, particularly to locate object boundaries. With conventional methods an object boundary can be extracted by controlling the internal energy and external energy based on energy minimization. However, this still leaves a number of problems, such as initialization and poor convergence in concave regions. In particular, a contour is unable to enter a concave region based on the stretching and bending characteristic of the internal energy. Therefore, this study proposes a method that controls the internal energy by moving the local perpendicular bisector point of each control point on the contour, and determines the object boundary by minimizing the energy relative to the external energy. Convergence at a concave region can then be effectively implemented as regards the feature of interest using the internal energy, plus several objects can be detected using a multi-detection method based on the initial contour. The proposed method is compared with other conventional methods through objective validation and subjective consideration. As a result, it is anticipated that the proposed method can be efficiently applied to the detection of the pulmonary parenchyma region in medical images.