• Journal of Advanced Navigation Technology
• /
• v.19 no.2
• /
• pp.133-139
• /
• 2015

This paper surveys vision based autonomous navigation technologies for unmanned systems. Main branches of visual navigation technologies are visual servoing, visual odometry, and visual simultaneous localization and mapping (SLAM). Visual servoing provides velocity input which guides mobile system to desired pose. This input velocity is calculated from feature difference between desired image and acquired image. Visual odometry is the technology that estimates the relative pose between frames of consecutive image. This can improve the accuracy when compared with the exisiting dead-reckoning methods. Visual SLAM aims for constructing map of unknown environment and determining mobile system's location simultaneously, which is essential for operation of unmanned systems in unknown environments. The trend of visual navigation is grasped by examining foreign research cases related to visual navigation technology.

• Journal of Positioning, Navigation, and Timing
• /
• v.2 no.1
• /
• pp.81-89
• /
• 2013

Many of the current visual odometry algorithms suffer from some extreme limitations such as requiring a high amount of computation time, complex algorithms, and not working in urban environments. In this paper, we present an approach that can solve all the above problems using a single camera. Using a planar motion assumption and Ackermann's principle of motion, we construct the vehicle's motion model as a circular planar motion (2DOF). Then, we adopt a 1-point method to improve the Ransac algorithm and the relative motion estimation. In the Ransac algorithm, we use a 1-point method to generate the hypothesis and then adopt the Levenberg-Marquardt method to minimize the geometric error function and verify inliers. In motion estimation, we combine the 1-point method with a simple least-square minimization solution to handle cases in which only a few feature points are present. The 1-point method is the key to speed up our visual odometry application to real-time systems. Finally, a Bundle Adjustment algorithm is adopted to refine the pose estimation. The results on real datasets in urban dynamic environments demonstrate the effectiveness of our proposed algorithm.

• Smart Structures and Systems
• /
• v.31 no.6
• /
• pp.561-571
• /
• 2023

Ensuring the safety of a structure necessitates that repairs are carried out based on accurate inspections and records of damage information. Traditional methods of recording damage rely on individual paper-based documents, making it challenging for inspectors to accurately record damage locations and track chronological changes. Recent research has suggested the adoption of building information modeling (BIM) to record detailed damage information; however, localizing damages on a BIM model can be time-consuming. To overcome this limitation, this study proposes a method to automatically localize damages on a BIM model in real-time, utilizing consecutive images and measurements from an inertial measurement unit in close proximity to damages. The proposed method employs a visual-inertial odometry algorithm to estimate the camera pose, detect damages, and compute the damage location in the coordinate of a prebuilt BIM model. The feasibility and effectiveness of the proposed method were validated through an experiment conducted on a campus building. Results revealed that the proposed method successfully localized damages on the BIM model in real-time, with a root mean square error of 6.6 cm.

• The Journal of Korea Robotics Society
• /
• v.14 no.2
• /
• pp.114-121
• /
• 2019

This paper presents a new benchmark system for visual odometry (VO) and monocular depth estimation (MDE). As deep learning has become a key technology in computer vision, many researchers are trying to apply deep learning to VO and MDE. Just a couple of years ago, they were independently studied in a supervised way, but now they are coupled and trained together in an unsupervised way. However, before designing fancy models and losses, we have to customize datasets to use them for training and testing. After training, the model has to be compared with the existing models, which is also a huge burden. The benchmark provides input dataset ready-to-use for VO and MDE research in 'tfrecords' format and output dataset that includes model checkpoints and inference results of the existing models. It also provides various tools for data formatting, training, and evaluation. In the experiments, the exsiting models were evaluated to verify their performances presented in the corresponding papers and we found that the evaluation result is inferior to the presented performances.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.11a
• /
• pp.47-48
• /
• 2022

The positioning technology that measures the position of a person or object is a key technology to deal with the location of the real coordinate system or converge the real and virtual worlds, such as digital twins, augmented reality, virtual reality, and autonomous driving. In estimating the location of a person or object at an indoor construction site, there are restrictions that it is impossible to receive location information from the outside, the communication infrastructure is insufficient, and it is difficult to install additional devices. Therefore, this study tested the direct sparse odometry algorithm, one of the visual Simultaneous Localization and Mapping (vSLAM) that estimate the current location and surrounding map using only image information, at an indoor construction site and analyzed its applicability as an indoor positioning technology. As a result, it was found that it is possible to properly estimate the surrounding map and the current location even in the indoor construction site, which has relatively few feature points. The results of this study can be used as reference data for researchers related to indoor positioning technology for construction sites in the future.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.46 no.6
• /
• pp.479-486
• /
• 2018

In order to ensure reliable navigation performance of a lunar exploration rover, navigation algorithms using additional sensors such as inertial measurement units and cameras are essential on lunar surface in the absence of a global navigation satellite system. Unprecedentedly, Visual Odometry (VO) using a stereo camera has been successfully implemented at the US Mars rovers. In this paper, we estimate the 6-DOF pose of the lunar exploration rover from gray images of a lunar-like terrains. The proposed algorithm estimates relative pose of consecutive images by sparse image alignment based semi-direct VO. In order to overcome vulnerability to non-linearity of direct VO, we add adaptive motion prior weights calculated from a linear function of the previous pose to the optimization cost function. The proposed algorithm is verified in lunar-like terrain dataset recorded by Toronto University reflecting the characteristics of the actual lunar environment.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.344-352
• /
• 2022

Accurate indoor localization of construction workers and mobile assets is essential in safety management. Existing positioning methods based on GPS, wireless, vision, or sensor based RTLS are erroneous or expensive in large-scale indoor environments. Tightly coupled sensor fusion mitigates these limitations. This research paper proposes a state-of-the-art positioning methodology, addressing the existing limitations, by integrating Stereo Visual Inertial Odometry (SVIO) with fiducial landmarks called AprilTags. SVIO determines the relative position of the moving assets or workers from the initial starting point. This relative position is transformed to an absolute position when AprilTag placed at various entry points is decoded. The proposed solution is tested on the NVIDIA ISAAC SIM virtual environment, where the trajectory of the indoor moving forklift is estimated. The results show accurate localization of the moving asset within any indoor or underground environment. The system can be utilized in various use cases to increase productivity and improve safety at construction sites, contributing towards 1) indoor monitoring of man machinery coactivity for collision avoidance and 2) precise real-time knowledge of who is doing what and where.

• Journal of Korea Multimedia Society
• /
• v.20 no.12
• /
• pp.1865-1873
• /
• 2017

The feature-based visual SLAM requires 3D positions for the extracted feature points to perform 3D-2D motion estimation. LiDAR can provide reliable and accurate 3D position information with low computational burden, while stereo camera has the problem of the impossibility of stereo matching in simple texture image region, the inaccuracy in depth value due to error contained in intrinsic and extrinsic camera parameter, and the limited number of depth value restricted by permissible stereo disparity. However, the sparsity of LiDAR data may increase the inaccuracy of motion estimation and can even lead to the result of motion estimation failure. Therefore, in this paper, we propose three interpolation methods which can be applied to interpolate sparse LiDAR data. Simulation results obtained by applying these three methods to a visual odometry algorithm demonstrates that the selective bilinear interpolation shows better performance in the view point of computation speed and accuracy.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.3
• /
• pp.107-111
• /
• 2021

A 3D point cloud map is an essential elements in various fields, including precise autonomous navigation system. However, generating a 3D point cloud map using a single sensor has limitations due to the price of expensive sensor. In order to solve this problem, we propose a precise 3D mapping system using low-cost sensor fusion. Generating a point cloud map requires the process of estimating the current position and attitude, and describing the surrounding environment. In this paper, we utilized a commercial visual-inertial odometry sensor to estimate the current position and attitude states. Based on the state value, the 2D LiDAR measurement values describe the surrounding environment to create a point cloud map. To analyze the performance of the proposed algorithm, we compared the performance of the proposed algorithm and the 3D LiDAR-based SLAM (simultaneous localization and mapping) algorithm. As a result, it was confirmed that a precise 3D point cloud map can be generated with the low-cost sensor fusion system proposed in this paper.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.1
• /
• pp.65-71
• /
• 2024

An indirect visual SLAM takes raw image data and exploits geometric information such as key-points and line edges. Due to various environmental changes, SLAM performance may decrease. The main problem is caused by dynamic objects especially in highly crowded environments. In this paper, we propose a robust feature-based visual SLAM, building on ORB-SLAM, via multi-channel dynamic objects estimation. An optical flow and deep learning-based object detection algorithm each estimate different types of dynamic object information. Proposed method incorporates two dynamic object information and creates multi-channel dynamic masks. In this method, information on actually moving dynamic objects and potential dynamic objects can be obtained. Finally, dynamic objects included in the masks are removed in feature extraction part. As a results, proposed method can obtain more precise camera poses. The superiority of our ORB-SLAM was verified to compared with conventional ORB-SLAM by the experiment using KITTI odometry dataset.