• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.5
• /
• pp.225-230
• /
• 2015

In this paper, we propose an effective real-time visual loop closure detector, VILODE, which makes use of key frames and bag of visual words (BoW) based on SURF feature points. In order to determine whether the camera has re-visited one of the previously visited places, a loop closure detector has to compare an incoming new image with all previous images collected at every visited place. As the camera passes through new places or locations, the amount of images to be compared continues growing. For this reason, it is difficult for a visual loop closure detector to meet both real-time constraint and high detection accuracy. To address the problem, the proposed system adopts an effective key frame selection strategy which selects and compares only distinct meaningful ones from continuously incoming images during navigation, and so it can reduce greatly image comparisons for loop detection. Moreover, in order to improve detection accuracy and efficiency, the system represents each key frame image as a bag of visual words, and maintains indexes for them using DBoW database system. The experiments with TUM benchmark datasets demonstrates high performance of the proposed visual loop closure detector.

• The Journal of Korea Robotics Society
• /
• v.7 no.2
• /
• pp.120-128
• /
• 2012

The loop closure problem is one of the most challenging issues in the vision-based simultaneous localization and mapping community. It requires the robot to recognize a previously visited place from current camera measurements. While the loop closure often relies on visual bag-of-words based on point features in the previous works, however, in this paper we propose a line-based method to solve the loop closure in the corridor environments. We used both the floor line and the anchored vanishing point as the loop closing feature, and a two-step loop closure algorithm was devised to detect a known place and perform the global pose correction. We propose an anchored vanishing point as a novel loop closure feature, as it includes position information and represents the vanishing points in bi-direction. In our system, the accumulated heading error is reduced using an observation of a previously registered anchored vanishing points firstly, and the observation of known floor lines allows for further pose correction. Experimental results show that our method is very efficient in a structured indoor environment as a suitable loop closure solution.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.5
• /
• pp.457-461
• /
• 2013

This paper proposes an image feature-based real-time RGB-D (Red-Green-Blue Depth) 3D SLAM (Simultaneous Localization and Mapping) system. RGB-D data from Kinect style sensors contain a 2D image and per-pixel depth information. 6-DOF (Degree-of-Freedom) visual odometry is obtained through the 3D-RANSAC (RANdom SAmple Consensus) algorithm with 2D image features and depth data. For speed up extraction of features, parallel computation is performed with GPU acceleration. After a feature manager detects a loop closure, a graph-based SLAM algorithm optimizes trajectory of the sensor and builds a 3D point cloud based map.

• The korean journal of orthodontics
• /
• v.25 no.5 s.52
• /
• pp.525-541
• /
• 1995

This study was designed to investigate force systems and tooth movements produced by retraction archwire during retraction of four maxillary incisors after the maxillary canine retraction into the maxillary first premolar extraction space using the computer-aided three-dimensional finite element method. A three-dimensional finite element model, consisting of 2248 elements and 3194 nodes, was constructed. The model consisted of maxillary teeth and surrounding periodontal membranes, .022'$\times$.028'-slot brackets, and 5 types of retraction archwires(.019'$\times$.025' stainless steel archwire) modeled using the beam elements. The contact between the wire and the bracket slot was modeled using the gap elements because of the non-linear elastic behaviors of the contact between them. The forces and moments, End displacements produced by retraction archwire were measured at various conditions to investigate the difference according to types of loops, magnitudes of activation force, gable angle, and anterior lingual root torque. The results were expressed quantitative and visual ways in the three-dimensional method. The following conclusions can be drawn from this study.1. When the tear-drop loop archwire was activated, the mesio-distal and lingual translational movements of the teeth helped to close the extraction space, but unwanted movements of the teeth including intrusions and extrusions, and rotational movements in each direction occurred. 2. Activation of T-loop archwire compared with those of other types of retraction archwires produced the least translational movements of the teeth helped to space closure and also the least unwanted movements of the teeth. 3. Increasing amount of activation in the tear-drop archwire led not only to increase of translational movements of the teeth helped to space closure, but also to increase of unwanted movements of the teeth. 4. Addition of gable bend in the tear-drop archwire helped anterior teeth to translational movements in the mesio-distal direction, but increased unwanted movements of the teeth 5. Addition of anterior lingual root torque in the tear-drop archwire helped central and lateral incisor to improve their facio-lingual inclination, but increased unwanted movements of the teeth.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.809-812
• /
• 2014

본 논문에서는 키 프레임 영상을 이용한 효과적인 실시간 시각 루프 결합 탐지기를 제안한다. 시각 루프 결합 탐지기는 과거에 지나온 위치들 중 하나를 다시 재방문하였는지를 판단하기 위해, 새로운 입력 영상을 이미 지나온 위치들에서 수집한 과거 영상들과 모두 비교해 보아야 한다. 따라서 새로운 위치나 장소를 방문할수록 비교 대상 영상들이 계속해서 증가하기 때문에, 일반적으로 루프 결합 탐지는 높은 정확도와 실시간성을 동시에 만족하기 어렵다. 이러한 문제점을 극복하기 위해, 본 시스템에서는 입력 영상들 중에서 키 프레임들만을 골라 비교함으로써, 루프 결합 탐지에 필요한 비교 연산량을 효과적으로 줄이는 방법을 채택하였다. 또한 본 시스템에서는 루프 결합 탐지의 정확도와 효율성을 높이기 위해, 키 프레임 영상들을 시각 단어들의 집합(BoW)으로 표현하고, DBoW 데이터베이스 시스템을 이용해 키 프레임 영상들에 대한 색인을 구성하였다. TUM 대학의 벤치마크 데이터들을 이용한 성능 분석 실험을 통해, 본 논문에서 제안한 시각 루프 결합 탐지기의 높은 성능을 확인할 수 있었다.