• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.373-380
• /
• 2022

This paper considers a method of fast correspondence matching for iterative closest point (ICP) algorithm. In robotics, the ICP algorithm and its variants have been widely used for pose estimation by finding the translation and rotation that best align two point clouds. In computational perspectives, the main difficulty is to find the correspondence point on the reference point cloud to each observed point. Jump-table-based correspondence matching is one of the methods for reducing computation time. This paper proposes a method that corrects errors in an existing jump-table-based correspondence matching algorithm. The criterion activating the use of jump-table is modified so that the correspondence matching can be applied to the situations, such as point-cloud registration problems with highly curved surfaces, for which the existing correspondence-matching method is non-applicable. For demonstration, both hardware and simulation experiments are performed. In a hardware experiment using Hokuyo-10LX LiDAR sensor, our new algorithm shows 100% correspondence matching accuracy and 88% decrease in computation time. Using the F1TENTH simulator, the proposed algorithm is tested for an autonomous driving scenario with 2D range-bearing point cloud data and also shows 100% correspondence matching accuracy.

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.4
• /
• pp.170-179
• /
• 1993

In this study, self-organized neural network is used to solve the vorrespondence problem of the axial stereo image. Edge points are extracted from a pair of stereo images and then the edge points of rear image are assined to the output nodes of neural network. In the matching process, the two input nodes of neural networks are supplied with the coordi- nates of the edge point selected randomly from the front image. This input data activate optimal output node and its neighbor nodes whose coordinates are thought to be correspondence point for the present input data, and then their weights are allowed to updated. After several iterations of updating, the weights whose coordinates represent rear edge point are converged to the coordinates of the correspondence points in the front image. Because of the feature map properties of self-organized neural network, noise-free and smoothed depth data can be achieved.

• Communications for Statistical Applications and Methods
• /
• v.12 no.1
• /
• pp.199-205
• /
• 2005

In general, simple correspondence analysis has handled mainly correspondence relations between the row and column categories but can not display the trends of their change over the time. For solving this problem, we will propose DSCA(Dynamic Simple Correspondence Analysis) of transition matrix data using supplementary categories in this study, Moreover, DSCA provides its trend of the change for the future by predicting and displaying trend toward the change from a standard point of time to the next.

• Journal of the Korean Dietetic Association
• /
• v.15 no.3
• /
• pp.298-310
• /
• 2009

The purposes of this study were to examine school foodservice employees' awareness on dietitians' service leadership and to analyze the effects of the service leadership on employee attitudes (leader reliability, value correspondence, and leader satisfaction). Questionnaires were distributed to 208 school foodservice employees from November 2007 to January 2008. The results were as follows. First, in terms of the employees' perception on the dietitians' service leadership, service belief gained the highest score, followed by insight, attitude, and ability: the average score was 3.8 point. Second, the leader reliability and leader satisfaction scores perceived by the employees were over 3.8 point on average but the awareness on the value correspondence was 3.43 point. Third, among the service leadership factors, service belief (p<0.001) and insight (p<0.001) had positive effects on leader reliability. Also, service belief (p<0.01), service ability (p<0.001), and insight (p<0.01) had positive effects on value correspondence. Finally, service belief (p<0.001), service ability (p<0.05), and insight (p<0.001) had positive effects on leader satisfaction. Fourth, a hypothesis test using path analysis revealed that dietitians' service leadership produced positive effects on school foodservice employees' attitudes (leader reliability, value correspondence, and leader satisfaction). In conclusion, the service leadership of dietitians directly contributed to leader satisfaction, value correspondence, and leader reliability in school foodservice employees.

• Journal of Korean Society for Geospatial Information Science
• /
• v.14 no.2 s.36
• /
• pp.23-32
• /
• 2006

This study shows that new methodology improved the problem of unaided eye test level with the digital orthophoto technique can survey more objectively and efficiently any cadastral non-coincidence than existing prior methodologies. For applying to it, we explore eligible other methodologies, and then build up the application strategy of them. New prototype system is implemented with it. Also, we say the availability of new methodology by applying to study area. As a result, we suggest cadastral non-coincidence surveying method based on point-correspondence more objective and more efficient. As a result of comparing with old method and new on same study area for making adequacy, they hardly ever has the difference of accuracy. Constantly, cadastral non-coincidence surveying method based on point-correspondence is acceptable way on the cadastral survey.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.2
• /
• pp.66-76
• /
• 1999

This paper proposes that can take at high speed the information of binocular disparity with moving translational and forward stereo camera to the extent that does not occur the problem of a correspondence point. It shows that in case of stereo vision with translational motion, can take the information of binocular disparity being devoid of error and putting high confidence in, and that in case of stereo vision with forward motion, can take the horizontal component which can not be detected in common stereo vision. Besides, the stereo vision can be done at high speed due to being bright and small a correspondence point comparing not to do, because a correspondence between right and left images is previously limited. But there are problem that a resonable information of binocular disparity can not be taken, if the vicinity of center of image is in accord with the region of occlusion in stereo vision with forward motion.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.5
• /
• pp.2310-2325
• /
• 2016

In this paper, we provide a trajectory-generation algorithm that can identify pedestrians in real time. Typically, the contours for the extraction of pedestrians from the foreground of images are not clear due to factors including brightness and shade; furthermore, pedestrians move in different directions and interact with each other. These issues mean that the identification of pedestrians and the generation of trajectories are somewhat difficult. We propose a new method for trajectory generation regarding multiple pedestrians. The first stage of the method distinguishes between those pedestrian-blob situations that need to be merged and those that require splitting, followed by the use of trained decision trees to separate the pedestrians. The second stage generates the trajectories of each pedestrian by using the point-correspondence method; however, we introduce a new point-correspondence algorithm for which the A* search method has been modified. By using fuzzy membership functions, a heuristic evaluation of the correspondence between the blobs was also conducted. The proposed method was implemented and tested with the PETS 2009 dataset to show an effective multiple-pedestrian-tracking capability in a pedestrian-interaction environment.

• Communications of the Korean Mathematical Society
• /
• v.17 no.2
• /
• pp.253-260
• /
• 2002

For an outer action $\alpha$ of a finite group G on a factor M, it was proved that H is a, normal subgroup of G if and only if there exists a finite group F and an outer action $\beta$ of F on the crossed product algebra M $\times$$_{\alpha}$ G = (M $\times$$_{\alpha}$ F. We generalize this to infinite group actions. For an outer action $\alpha$ of a discrete group, we obtain a Galois correspondence for crossed product algebras related to normal subgroups. When $\alpha$ satisfies a certain condition, we also obtain a Galois correspondence for fixed point algebras. Furthermore, for a minimal action $\alpha$ of a compact group G and a closed normal subgroup H, we prove $M^{G}$ = ( $M^{H}$)$^{{beta}(G/H)}$for a minimal action $\beta$ of G/H on $M^{H}$.f G/H on $M^{H}$.TEX> H/.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.4
• /
• pp.242-249
• /
• 2011

In this paper, the correspondence matching method of stereo images was proposed by means of sampling projective transformation matrix in planar region of scene. Though this study is based on RANSAC, it does not use uniform distribution by random sampling in RANSAC, but use multi non-uniform computed from difference in positions of feature point of image or templates matching. The existing matching method sampled that the correspondence is presumed to correct by use of the condition which the correct correspondence is almost satisfying, and applied RANSAC by matching the correspondence into one to one, but by sampling in stages in multi probability distribution computed for image in the proposed method, the correct correspondence of high probability can be sampled among multi correspondence candidates effectively. In the result, we could obtain many correct correspondence and verify effectiveness of the proposed method in the simulation and experiment of real images.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.6_1
• /
• pp.529-536
• /
• 2007

Registration between image and object space is a fundamental step in photogrammetry and computer vision. Along with rapid development of sensors - multi/hyper spectral sensor, laser scanning sensor, radar sensor etc., the needs for registration between different sensors are ever increasing. There are two important considerations on different sensor registration. They are sensor invariant feature extraction and correspondence between them. Since point to point correspondence does not exist in image and laser scanning data, it is necessary to have higher entities for extraction and correspondence. This leads to modify first, existing mathematical and geometrical model which was suitable for point measurement to line measurements, second, matching scheme. In this research, linear feature is selected for sensor invariant features and matching entity. Linear features are incorporated into mathematical equation in the form of extended collinearity equation for registration problem known as photo resection which calculates exterior orientation parameters. The other emphasis is on the scheme of finding matched entities in the aide of RANSAC (RANdom SAmple Consensus) in the absence of correspondences. To relieve computational load which is a common problem in sampling theorem, deterministic sampling technique and selecting 4 line features from 4 sectors are applied.