• The Journal of Korea Robotics Society
• /
• v.3 no.4
• /
• pp.263-269
• /
• 2008

Visual odometry is a popular approach to estimating robot motion using a monocular or stereo camera. This paper proposes a novel visual odometry scheme using a stereo camera for robust estimation of a 6 DOF motion in the dynamic environment. The false results of feature matching and the uncertainty of depth information provided by the camera can generate the outliers which deteriorate the estimation. The outliers are removed by analyzing the magnitude histogram of the motion vector of the corresponding features and the RANSAC algorithm. The features extracted from a dynamic object such as a human also makes the motion estimation inaccurate. To eliminate the effect of a dynamic object, several candidates of dynamic objects are generated by clustering the 3D position of features and each candidate is checked based on the standard deviation of features on whether it is a real dynamic object or not. The accuracy and practicality of the proposed scheme are verified by several experiments and comparisons with both IMU and wheel-based odometry. It is shown that the proposed scheme works well when wheel slip occurs or dynamic objects exist.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.9
• /
• pp.738-744
• /
• 2016

In this paper, a robust visual odometry system has been proposed and implemented in an environment with dynamic illumination. Visual odometry is based on stereo images to estimate the distance to an object. It is very difficult to realize a highly accurate and stable estimation because image quality is highly dependent on the illumination, which is a major disadvantage of visual odometry. Therefore, in order to solve the problem of low performance during the feature detection phase that is caused by illumination variations, it is suggested to determine an optimal threshold value in the image binarization and to use an adaptive threshold value for feature detection. A feature point direction and a magnitude of the motion vector that is not uniform are utilized as the features. The performance of feature detection has been improved by the RANSAC algorithm. As a result, the position of a mobile robot has been estimated using the feature points. The experimental results demonstrated that the proposed approach has superior performance against illumination variations.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.10
• /
• pp.958-964
• /
• 2015

In this paper, an object recognition method based on the depth information from the RGB-D camera, Xtion, is proposed for an indoor mobile robot. First, the RANdom SAmple Consensus (RANSAC) algorithm is applied to the point cloud obtained from the RGB-D camera to detect and remove the floor points. Next, the removed point cloud is classified by the k-means clustering method as each object's point cloud, and the normal vector of each point is obtained by using the k-d tree search. The obtained normal vectors are classified by the trained multi-layer perceptron as 18 classes and used as features for object recognition. To distinguish an object from another object, the similarity between them is measured by using Levenshtein distance. To verify the effectiveness and feasibility of the proposed object recognition method, the experiments are carried out with several similar boxes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.302-320
• /
• 2017

In this paper, an innovative robust feature detection and matching strategy for visual odometry based on stereo image sequence is proposed. First, a sparse multiscale 2D local invariant feature detection and description algorithm AKAZE is adopted to extract the interest points. A robust feature matching strategy is introduced to match AKAZE descriptors. In order to remove the outliers which are mismatched features or on dynamic objects, an improved random sample consensus outlier rejection scheme is presented. Thus the proposed method can be applied to dynamic environment. Then, geometric constraints are incorporated into the motion estimation without time-consuming 3-dimensional scene reconstruction. Last, an iterated sigma point Kalman Filter is adopted to refine the motion results. The presented ego-motion scheme is applied to benchmark datasets and compared with state-of-the-art approaches with data captured on campus in a considerably cluttered environment, where the superiorities are proved.

• Journal of the Society of Naval Architects of Korea
• /
• v.59 no.4
• /
• pp.235-242
• /
• 2022

As ship condition inspection technology has been developed, research on collecting, analyzing, and diagnosing condition information has become active. In ships, related research has been conducted, such as analyzing, detecting, and classifying major hull failures such as cracks and corrosion using 2D and 3D data information. However, for geometric deformation such as indents and bulges, 2D data has limitations in detection, so 3D data is needed to utilize spatial feature information. In this study, we aim to detect hull structural deformation positions. It builds a specimen based on actual hull structure deformation and acquires a point cloud from a model scanned with a 3D scanner. In the obtained point cloud, deformation(outliers) is found with a combination of RANSAC algorithms that find the best matching model in the Octree data structure and dataset.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.2
• /
• pp.525-531
• /
• 2015

According to the increasing demand for 3D indoor spatial information, the utilization of a terrestrial laser scanner comes to the fore. However, the research for the comparison between a terrestrial laser scanning method and a traditional surveying method is insufficient. The paper evaluated the time-efficiency and the locational accuracy of an AMCW type and a direct TOF type of terrestrial laser scanning methods in comparison with the observation using a total station. As a result, an AMCW type showed higher time-efficiency than a direct TOF type and the RMSE between the two types of data was ${\pm}1mm$. Moreover, the terrestrial laser scanning method showed twice higher time-efficiency than the observation using a total station and the RMSE between the two data was ${\pm}3.4cm$. The results indicate that the terrestrial laser scanning method has better profitability and performance for 3D indoor modeling than the traditional survey using a total station. In the future, a terrestrial laser scanner can be efficiently utilized in the construction of 3D indoor spatial information.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.8
• /
• pp.65-75
• /
• 2013

This paper proposes a method of tracking the hand region and detecting the fingertip using only depth images. In order to eliminate the influence of lighting conditions and obtain information quickly and stably, this paper proposes a tracking method that relies only on depth information, as well as a method of using region growing to identify errors that can occur during the tracking process and a method of detecting the fingertip that can be applied for the recognition of various gestures. First, the closest point of approach is identified through the process of transferring the center point in order to locate the tracking point, and the region is grown from that point to detect the hand region and boundary line. Next, the ratio of the invalid boundary, obtained by means of region growing, is used to calculate the validity of the tracking region and thereby judge whether the tracking is normal. If tracking is normal, the contour line is extracted from the detected hand region and the curvature and RANSAC and Convex-Hull are used to detect the fingertip. Lastly, quantitative and qualitative analyses are performed to verify the performance in various situations and prove the efficiency of the proposed algorithm for tracking and detecting the fingertip.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.220-223
• /
• 2004

Automatic image registration is an essential element of remote sensing because remote sensing system generates enormous amount of data, which are multiple observations of the same features at different times and by different sensor. The general process of automatic image registration includes three steps: 1) The extraction of features to be used in the matching process, 2) the feature matching strategy and accurate matching process, 3) the resampling of the data based on the correspondence computed from matched feature. For step 2) and 3), we have developed an algorithms for automated registration of satellite images with RANSAC(Random Sample Consensus) in success. However, for step 1), There still remains human operation to generate GCP Chips, which is time consuming, laborious and expensive process. The main idea of this research is that we are able to automatically generate GCP chips with comer detection algorithms without GPS survey and human interventions if we have systematic corrected satellite image within adaptable positional accuracy. In this research, we use SUSAN(Smallest Univalue Segment Assimilating Nucleus) algorithm in order to detect the comer. SUSAN algorithm is known as the best robust algorithms for comer detection in the field of compute vision. However, there are so many comers in high-resolution images so that we need to reduce the comer points from SUSAN algorithms to overcome redundancy. In experiment, we automatically generate GCP chips from IKONOS images with geo level using SUSAN algorithms. Then we extract reference coordinate from IKONOS images and DEM data and filter the comer points using texture analysis. At last, we apply automatically collected GCP chips by proposed method and the GCP by operator to in-house automatic precision correction algorithms. The compared result will be presented to show the GCP quality.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.792-799
• /
• 2022

Building Information Modeling (BIM) technology is a key component of modern construction engineering and project management workflows. As-is BIM models that represent the spatial reality of a project site can offer crucial information to stakeholders for construction progress monitoring, error checking, and building maintenance purposes. Geometric methods for automatically converting raw scan data into BIM models (Scan-to-BIM) often fail to make use of higher-level semantic information in the data. Whereas, semantic segmentation methods only output labels at the point level without creating object level models that is necessary for BIM. To address these issues, this research proposes a hybrid semantic-geometric approach for clutter-resistant floorplan generation from laser-scanned building point clouds. The input point clouds are first pre-processed by normalizing the coordinate system and removing outliers. Then, a semantic segmentation network based on PointNet++ is used to label each point as ceiling, floor, wall, door, stair, and clutter. The clutter points are removed whereas the wall, door, and stair points are used for 2D floorplan generation. A region-growing segmentation algorithm paired with geometric reasoning rules is applied to group the points together into individual building elements. Finally, a 2-fold Random Sample Consensus (RANSAC) algorithm is applied to parameterize the building elements into 2D lines which are used to create the output floorplan. The proposed method is evaluated using the metrics of precision, recall, Intersection-over-Union (IOU), Betti error, and warping error.

• Korean Journal of Remote Sensing
• /
• v.30 no.4
• /
• pp.431-444
• /
• 2014

As applications of spaceborne SAR imagery are extended, there are increased demands for accurate registrations for better understanding and fusion of radar images. It becomes common to adopt multi-resolution SAR images to apply for wide area reconnaissance. Geometric correction of the SAR images can be performed by using satellite orbit and attitude information. However, the inherent errors of the SAR sensor's attitude and ground geographical data tend to cause geometric errors in the produced SAR image. These errors should be corrected when the SAR images are applied for multi-temporal analysis, change detection applications and image fusion with other sensor images. The undesirable ground registration errors can be corrected with respect to the true ground control points in order to produce complete SAR products. Speeded Up Robust Feature (SURF) technique is an efficient algorithm to extract ground control points from images but is considered to be inappropriate to apply to SAR images due to high speckle noises. In this paper, an attempt is made to apply SURF algorithm to SAR images for image registration and fusion. Matched points are extracted with respect to the varying parameters of Hessian and SURF matching thresholds, and the performance is analyzed by measuring the imaging matching accuracies. A number of performance measures concerning image registration are suggested to validate the use of SURF for spaceborne SAR images. Various simulations methodologies are suggested the validate the use of SURF for the geometric correction and image registrations and it is shown that a good choice of input parameters to the SURF algorithm should be made to apply for the spaceborne SAR images of moderate resolutions.