Beom-Su Seo

Assistive Guidance System Based on Online Path Structure Recognition for the Visually Impaired

Jae-Yeong Lee, Yongseop Jeong, Seung‐Min Choi, Beom-Su Seo

Independent mobility is essential for visually impaired individuals, yet existing mobility aids such as white canes and guide dogs have limitations in accessibility and effectiveness. To address this, we propose an assistive robotic guidance system that replicates key functionalities of guide dogs. …

kr (code pays fourni par la source)

Fusion of 3D-2D Data for Drivable Area Detection and Road Condition Analysis in Assistive Quadruped Robots for the Visually Impaired

Jiho Chang, Beom-Su Seo

This paper presents a system designed for a quadruped robot that assists visually impaired individuals by analyzing road conditions and detecting drivable areas. The system integrates 3D point cloud data from Lidar with 2D semantic segmentation from RGB cameras, enabling a comprehensive …

kr (code pays fourni par la source)

MPI System with Bore Sizes of 75 mm and 100 mm Using Permanent Magnets and FMMD Technique

Jae Chan Jeong, Tae Yi Kim, Hyeon Sung Cho, Beom-Su Seo et autres

We present two magnetic particle imaging (MPI) systems with bore sizes of 75 mm and 100 mm, respectively, using three-dimensionally arranged permanent magnets for excitation and frequency mixing magnetic detection (FMMD) coils for detection. A rotational and a translational stage were combined …

kr, de (code pays fourni par la source)

A Novel Field-Free Line Generator for Mechanically Scanned Magnetic Particle Imaging

Tae Yi Kim, Jae Chan Jeong, Beom-Su Seo, Hans‐Joachim Krause et autres

In this study, we propose an efficient field-free line (FFL) generator for mechanically driven FFL magnetic particle imaging (MPI) applications. The novel FFL generator comprises pairs of Halbach arrays and bar magnets. The proposed design generates high-gradient FFLs with low-mass permanent magnets, …

kr, de (code pays fourni par la source)

Novel Field-Free Line Generator for Mechanically Scanned Magnetic Particle Imaging

Tae Yi Kim, Jae Chan Jeong, Beom-Su Seo, Hans‐Joachim Krause et autres

In this study, we propose an efficient field-free line (FFL) generator for mechanically driven FFL-magnetic particle imaging (MPI) applications. The novel FFL generator comprises pairs of Halbach arrays and bar magnets. The proposed design generates high-gradient FFLs with low-mass permanent magnets, realizing …

kr, de (code pays fourni par la source)

Sensing Range Extension for Short-Baseline Stereo Camera Using Monocular Depth Estimation

Beom-Su Seo, Byungjae Park, Hoon Choi

This paper proposes a method to extend a sensing range of a short-baseline stereo camera (SBSC). The proposed method combines a stereo depth and a monocular depth estimated by a convolutional neural network-based monocular depth estimation (MDE). To combine a stereo depth …

kr (code pays fourni par la source)

Magnetic Particle Imaging Using Moving Halbach Cuboid and Frequency Mixing Magnetic Detection

Jae‐chan Jeong, Jinsun Kim, Beom-Su Seo, Hans Krause et autres

Abstract We present a magnetic particle imaging (MPI) device using a Halbach cuboid magnet and frequency mixing magnetic detection (FMMD) technology. A Field Free Line was formed in the center of a two-piece Halbach cuboid. Then, the cuboid was moved in the …

kr, de (code pays fourni par la source)

Improvement in Deep Networks for Optimization Using eXplainable Artificial Intelligence

Jin Ha Lee, Ik hee Shin, Sang gu Jeong, Seung‐Ik Lee et autres

With the recent advancements in the field of explainable artificial intelligence (XAI), which covers the domain of turning deep network architectures from black boxes to comprehensible structures, it became easy to understand what goes on inside a network when it predicts an …

ye (code pays fourni par la source)

A Brief Survey on Contemporary Methods for Anomaly Detection in Videos

Muhammad Zaigham Zaheer, Jin Ha Lee, Seung‐Ik Lee, Beom-Su Seo

Anomaly detection has stayed among the core topics of research in machine learning and computer vision for decades. Due to its complex nature, limitless possibilities of abnormal cases and the bounded amount of normal examples available, it is still among the popular …

kr (code pays fourni par la source)

A study on resilient back-propagation neural network model for estimation of welding properties of flux cored wire

Juyong Park, Beom-Su Seo

LiDAR Image Segmentation using Convolutional Neural Network Model with Refinement Modules

Byungjae Park, Beom-Su Seo, Sejin Lee

Rank selection of CP-decomposed convolutional layers with variational Bayesian matrix factorization

Marcella Astrid, Seung‐Ik Lee, Beom-Su Seo

Convolutional Neural Networks (CNNs) is one of successful method in many areas such as image classification tasks. However, the amount of memory and computational cost needed for CNNs inference obstructs them to run efficiently in mobile devices because of memory and computational …

kr (code pays fourni par la source)