• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.12
• /
• pp.1021-1026
• /
• 2016

The graph-based SLAM (Simultaneous Localization and Mapping) approach has been gaining much attention in SLAM research recently thanks to its ability to provide better maps and full trajectory estimations when compared to the filtering-based SLAM approach. Even though graph-based SLAM requires batch processing causing it to be computationally heavy, recent advancements in optimization and computing power enable it to run fast enough to be used in real-time. However, data association problems still require large amount of computation when building a pose graph. For example, to find loop closures it is necessary to consider the whole history of the robot trajectory and sensor data within the confident range. As a pose graph grows, the number of candidates to be searched also grows. It makes searching the loop closures a bottleneck when solving the SLAM problem. Our approach to alleviate this bottleneck is to sample a limited number of pose nodes in which loop closures are searched. We propose a heuristic for sampling pose nodes that are most advantageous to closing loops by providing a way of ranking pose nodes in order of usefulness for closing loops.

• The Journal of Korea Robotics Society
• /
• v.12 no.4
• /
• pp.385-394
• /
• 2017

Side scanning sonar (SSS) provides valuable information for robot navigation. However using the side scanning sonar images in the navigation was not fully studied. In this paper, we use range data, and side scanning sonar images from UnderWater Simulator (UWSim) and propose measurement models in a feature based simultaneous localization and mapping (SLAM) framework. The range data is obtained by echosounder and sidescanning sonar images from side scan sonar module for UWSim. For the feature, we used the A-KAZE feature for the SSS image matching and adjusting the relative robot pose by SSS bundle adjustment (BA) with Ceres solver. We use BA for the loop closure constraint of pose-graph SLAM. We used the Incremental Smoothing and Mapping (iSAM) to optimize the graph. The optimized trajectory was compared against the dead reckoning (DR).

• The Journal of Korea Robotics Society
• /
• v.10 no.2
• /
• pp.112-118
• /
• 2015

This paper proposes a pose-graph based SLAM method using an upward-looking camera and artificial landmarks for AGVs in factory environments. The proposed method provides a way to acquire the camera extrinsic matrix and improves the accuracy of feature observation using a low-cost camera. SLAM is conducted by optimizing AGV's explored path using the artificial landmarks installed on the ceiling at various locations. As the AGV explores, the pose nodes are added based on the certain distance from odometry and the landmark nodes are registered when AGV recognizes the fiducial marks. As a result of the proposed scheme, a graph network is created and optimized through a G2O optimization tool so that the accumulated error due to the slip is minimized. The experiment shows that the proposed method is robust for SLAM in real factory environments.

• Smart Structures and Systems
• /
• v.14 no.5
• /
• pp.943-960
• /
• 2014

A visually servoed paired structured light system (ViSP) was recently proposed as a novel estimation method of the 6-DOF (Degree-Of-Freedom) relative displacement in civil structures. In order to apply the ViSP to massive structures, multiple ViSP modules should be installed in a cascaded manner. In this configuration, the estimation errors are propagated through the ViSP modules. In order to resolve this problem, a displacement estimation error back-propagation (DEEP) method was proposed. However, the DEEP method has some disadvantages: the displacement range of each ViSP module must be constrained and displacement errors are corrected sequentially, and thus the entire estimation errors are not considered concurrently. To address this problem, a pose-graph optimized displacement estimation (PODE) method is proposed in this paper. The PODE method is based on a graph-based optimization technique that considers entire errors at the same time. Moreover, this method does not require any constraints on the movement of the ViSP modules. Simulations and experiments are conducted to validate the performance of the proposed method. The results show that the PODE method reduces the propagation errors in comparison with a previous work.

• Journal of the Korean Mathematical Society
• /
• v.42 no.6
• /
• pp.1251-1264
• /
• 2005

Let D be an acyclic digraph. The competition graph of D has the same set of vertices as D and an edge between vertices u and v if and only if there is a vertex x in D such that (u, x) and (v, x) are arcs of D. The competition number of a graph G, denoted by k(G), is the smallest number k such that G together with k isolated vertices is the competition graph of an acyclic digraph. It is known to be difficult to compute the competition number of a graph in general. Even characterizing the graphs with competition number one looks hard. In this paper, we continue the work done by Cho and Kim[3] to characterize the graphs with one hole and competition number one. We give a sufficient condition for a graph with one hole to have competition number one. This generates a huge class of graphs with one hole and competition number one. Then we completely characterize the graphs with one hole and competition number one that do not have a vertex adjacent to all the vertices of the hole. Also we show that deleting pendant vertices from a connected graph does not change the competition number of the original graph as long as the resulting graph is not trivial, and this allows us to construct infinitely many graph having the same competition number. Finally we pose an interesting open problem.

• Journal of Information Processing Systems
• /
• v.15 no.1
• /
• pp.67-90
• /
• 2019

Accurate detection, tracking and analysis of human movement using robots and other visual surveillance systems is still a challenge. Efforts are on to make the system robust against constraints such as variation in shape, size, pose and occlusion. Traditional methods of detection used the sliding window approach which involved scanning of various sizes of windows across an image. This paper concentrates on employing a state-of-the-art, hierarchical graph based method for segmentation. It has two stages: part level segmentation for color-consistent segments and object level segmentation for category-consistent regions. The tracking phase is achieved by employing SIFT keypoint descriptor based technique in a combined matching and tracking scheme with validation phase. Localization of human region in each frame is performed by keypoints by casting votes for the center of the human detected region. As it is difficult to avoid incorrect keypoints, a consensus-based framework is used to detect voting behavior. The designed methodology is tested on the video sequences having 3 to 4 persons.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.11-14
• /
• 2000

In this paper, we propose a fast and practical head pose estimation scheme fur eye-head controlled human computer interface with non-constrained background. The method we propose uses complete graph matching from thresholded images and the two blocks showing the greatest similarity are selected as eyes, we also locate mouth and nostrils in turn using the eye location information and size information. The average computing time of the image(360*240) is within 0.2(sec) and we employ template matching method using angles between facial features for head pose estimation. It has been tested on several sequential facial images with different illuminating conditions and varied head poses, It returned quite a satisfactory performance in both speed and accuracy.

• The Journal of Korea Robotics Society
• /
• v.4 no.3
• /
• pp.185-191
• /
• 2009

This paper presents a new shape-based algorithm using affine category shape model for object category recognition and model learning. Affine category shape model is a graph of interconnected nodes whose geometric interactions are modeled using pairwise potentials. In its learning phase, it can efficiently handle large pose variations of objects in training images by estimating 2-D homography transformation between the model and the training images. Since the pairwise potentials are defined on only relative geometric relationship betweenfeatures, the proposed matching algorithm is translation and in-plane rotation invariant and robust to affine transformation. We apply spectral matching algorithm to find feature correspondences, which are then used as initial correspondences for RANSAC algorithm. The 2-D homography transformation and the inlier correspondences which are consistent with this estimate can be efficiently estimated through RANSAC, and new correspondences also can be detected by using the estimated 2-D homography transformation. Experimental results on object category database show that the proposed algorithm is robust to pose variation of objects and provides good recognition performance.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.114-117
• /
• 2009

A new video inpainting algorithm is proposed for removing unwanted objects or error of sources from video data. In the first step, the block bundle is defined by the motion information of the video data to keep the temporal consistency. Next, the block bundles are arranged in the 3-dimensional graph that is constructed by the spatial and temporal correlation. Finally, we pose the inpainting problem in the form of a discrete global optimization and minimize the objective function to find the best temporal bundles for the grid points. Extensive simulation results demonstrate that the proposed algorithm yields visually pleasing video inpainting results even in a dynamic scene.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.2
• /
• pp.84-91
• /
• 2009

This paper presents an online partial 3D modeling methodology that uses a mobile augmented reality system and aerial photographs, and a tracking methodology that compares the 3D model with a video image. Instead of relying on models which are created in advance, the system generates a 3D model for a real building on the fly by combining frontal and aerial views. A user's initial pose is estimated using an aerial photograph, which is retrieved from a database according to the user's GPS coordinates, and an inertial sensor which measures pitch. We detect edges of the rooftop based on Graph cut, and find edges and a corner of the bottom by minimizing the proposed cost function. To track the user's position and orientation in real-time, feature-based tracking is carried out based on salient points on the edges and the sides of a building the user is keeping in view. We implemented camera pose estimators using both a least squares estimator and an unscented Kalman filter (UKF). We evaluated the speed and accuracy of both approaches, and we demonstrated the usefulness of our computations as important building blocks for an Anywhere Augmentation scenario.