• ETRI Journal
• /
• v.45 no.5
• /
• pp.836-846
• /
• 2023

Mobile robots are used in modern life; however, object recognition is still insufficient to realize robot navigation in crowded environments. Mobile robots must rapidly and accurately recognize the movements and shapes of pedestrians to navigate safely in pedestrian-rich spaces. This study proposes real-time, accurate, three-dimensional (3D) multi-pedestrian detection and tracking using a 3D light detection and ranging (LiDAR) point cloud in crowded environments. The pedestrian detection quickly segments a sparse 3D point cloud into individual pedestrians using a lightweight convolutional autoencoder and connected-component algorithm. The multi-pedestrian tracking identifies the same pedestrians considering motion and appearance cues in continuing frames. In addition, it estimates pedestrians' dynamic movements with various patterns by adaptively mixing heterogeneous motion models. We evaluate the computational speed and accuracy of each module using the KITTI dataset. We demonstrate that our integrated system, which rapidly and accurately recognizes pedestrian movement and appearance using a sparse 3D LiDAR, is applicable for robot navigation in crowded spaces.

• 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.

• Journal of the Society of Naval Architects of Korea
• /
• v.45 no.4
• /
• pp.462-467
• /
• 2008

In this paper, we investigated the design method of mooring system in ultra deep sea and carried out the conceptual design for offshore West Africa oil field in ultra deep sea of 3000 meters. Recently, it was feasible to design and install the offshore floating structures in deep sea of up to 2000 meters. Due to the simplicity, two-point mooring design is fully utilized. Force-excursion curves are throughly examined to find out the feasibility of various combinations of mooring lines. Free length and pretension effects are discussed. It is found that composite materials including synthetic fiber rope may be good solution for ultra deep sea mooring design.

• International Journal of Aeronautical and Space Sciences
• /
• v.18 no.3
• /
• pp.403-413
• /
• 2017

Dual-point aerodynamic design optimization is conducted for DLR-F6 wing-body-nacelle-pylon configuration adopting an efficient surface mesh movement method for complex junction geometries. A three-dimensional unstructured Euler solver and its discrete adjoint code are utilized for flow and sensitivity analysis, respectively. Considered design conditions are a low-lift condition and a cruise condition in a transonic regime. Design objective is to minimize drag and reduce shock strength at both flow conditions. Shape deformation is made by variation of the section shapes of inboard wing and pylon, nacelle vertical location and nacelle pitch angle. Hicks-Henne shape functions are employed for deformation of the section shapes of wing and pylon. By the design optimization, drag coefficients were remarkably reduced at both design conditions retaining specified lift coefficient and satisfying other constraints. Two-point design results show mixed features of the one-point design results at low-lift condition and cruise conditions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.422-424
• /
• 2021

In this paper, it leads the approach of fusing multiple RGB cameras for visual objects recognition based on deep learning with convolution neural network and 3D Light Detection and Ranging (LiDAR) to observe the environment and match into a 3D world in estimating the distance and position in a form of point cloud map. The goal of perception in multiple cameras are to extract the crucial static and dynamic objects around the autonomous vehicle, especially the blind spot which assists the AV to navigate according to the goal. Numerous cameras with object detection might tend slow-going the computer process in real-time. The computer vision convolution neural network algorithm to use for eradicating this problem use must suitable also to the capacity of the hardware. The localization of classified detected objects comes from the bases of a 3D point cloud environment. But first, the LiDAR point cloud data undergo parsing, and the used algorithm is based on the 3D Euclidean clustering method which gives an accurate on localizing the objects. We evaluated the method using our dataset that comes from VLP-16 and multiple cameras and the results show the completion of the method and multi-sensor fusion strategy.

• Proceedings of the IEEK Conference
• /
• 2004.06a
• /
• pp.301-304
• /
• 2004

In this paper, we propose a method to find the optimal direction of the multi beam between each station on the point-to-point link by genetic algorithm. In the proposed method, maximum value in optimal direction on each station is used as a fitness function. The beam of millimeter wave generates a lot of multi-peak because of much influence of noise. About each gene, we simulated this method using 16bit, 32bit, and 32bit split algorithm. 32bit split uses 16bit gene information. Each antenna makes 32bit gene information by adding gene information of two antennas having 16bit gene. Through the proposed method, we could have gotten a good output without 32bit gene information.

• Proceedings of the KIPE Conference
• /
• 2016.07a
• /
• pp.231-232
• /
• 2016

This paper investigates the design of multi-winding coupled inductor for minimum inductor current ripple. Based on the general circuit model of coupled inductor together with the operating principles of dc-dc converter, the relationship between the ripple size of inductor current and the coupling factor is derived under the different duty ratio. The optimal coupling factor of n-phase multi-winding coupled inductor which corresponds to a minimum inductor ripple current becomes -(1/n-1), i.e. a complete inverse coupling without leakage inductance, as the duty ratio of steady-state operating point approaches 1/n, 2/n, ${\cdots}$ or (n-1)/n. In an opposite manner, the optimal coupling factor value of zero, i.e. zero mutual inductance, is required when the duty ratio of steady-state operating point approaches either zero or one. Therefore, coupled inductors having optimal coupling factor can minimize the ripple current of inductor and inductor size.

• Journal of Korean Society for Quality Management
• /
• v.14 no.1
• /
• pp.26-32
• /
• 1986

A class of multi-factor designs for estimating the slope of second order response surfaces is presented. For multi-factor designs the variance of the estimated slope at a point is a function of the direction of measurement of the slope and the design. If we average the variance over all possible directions, the averaged variance is only a function of the point and the design. By choice of design, it is possible to make this variance constant for all points equidistant from the design origin. This property is called "slope-rotatability over all directions", and the necessary and sufficient conditions for a design to have this property are given and proved. The class of design with this property is mainly discussed.

• Journal of Power System Engineering
• /
• v.16 no.6
• /
• pp.86-91
• /
• 2012

A multi purpose environmental monitoring system has been developed as a commercially available standard using the techniques which are FBG(Fiber Bragg Grating), Hetero-core spliced fiber optic sensor and etc, for the purposes of monitoring large scaled structures and preserving natural environments. The monitoring system has been tested and evaluated in a possible outdoor condition in view of the full scaled operation at actual sites to be monitored. Additionally, the developed systems in the previous works conveniently provided us with various options of sensor modules intended for monitoring such physical quantities as displacement, distortion, pressure, binary states, and liquid adhesion. In this paper, we extend the previous results to a water leakage detection problem and develop a sensing system as a result. By the experimental study, it is verified that multi-point leakage detection is possible using single line optical fiber.

• The KSFM Journal of Fluid Machinery
• /
• v.13 no.3
• /
• pp.37-42
• /
• 2010

This study investigated on details of flow characteristics of a multi-blade fan for domestic ventilation. Experiments and analysis were carried out to describe on flow pattern with variations of cut-off angle near the scroll housing throat, which were performed by PIV measurement for the flow field and by total pressure probes. The stagnation point at cut-off region of the fan moves to the exit of the scroll housing as the cut-off angle increases. The movement of stagnation point and the variation of throat area of the scroll housing influence to the distribution of velocity magnitude at the exit of the fan. Furthermore, a large distortion of the velocity distribution at the scroll exit causes to increase mixing loss along the flow path.