Kien Trung Nguyen

장한용

신현주

엄기원

김영범

백승호

강형엽

김상빈

조성익

김승욱

강인구

손홍정

김현우

정택상

지현호

이효일

하동욱

국종률

김경민

김동영

조용현

박광현

김광혁

김동석

Luhur Pidekso Arif

윤원배

이남일

심예람

손한성

이신재

한구현

Tanh Quang Tran

김명곤

최진우

Paul C. Gloumeau

박승빈

권성수

박인범

이건선

유기현

조준엽

이종민

도재형

이재현

손재민

채주환

정승원

안준성

Hong Son Nguyen

The Korea University Media Lab focuses on Computer Graphics and Vision for Game and Entertainment and Augmented Reality for Industrial Applications. The lab is always looking for undergraduate researchers, graduate students (Master's and Ph.D.), short-term interns, research professors and full-time researchers.

고려대학교 미디어 연구실은 게임 및 엔터테인먼트 분야의 컴퓨터 그래픽스와 비전, 산업 응용 분야의 증강 현실에 중점을 둔다. 학부 연구생, 석박사 과정 대학원생, 단기 인턴, 전임 연구원, 연구 교수를 상시 모집한다.

The field of solid modeling has developed a variety of techniques for unambiguous representations of three-dimensional objects. Feature recognition is a sub-discipline of solid modeling that focuses on the design and implementation of algorithms for detecting manufacturing information from solid models produced by computer-aided design (CAD) systems. Examples of this manufacturing information include features such as holes, slots, pockets and other shapes that can be created on modern computer numerically controlled machining systems. Automated feature recognition has been an active research area in solid modeling for many years and is considered to be a critical component for integration of CAD and computer-aided manufacturing. The paper gives an overview of the state-of-the-art in feature recognition research. Rather than giving an exhaustive survey, we focus on the three of the major algorithmic …

Manufacturing feature recognition from solid models: a status report

Process planning for machined parts typically requires that a part be described through machining features such as holes, slots and pockets. This paper presents a novel feature finder, which automatically generates a part interpretation in terms of machining features, by utilizing information from a variety of sources such as nominal geometry, tolerances and attributes, and design features. The feature finder strives to produce a desirable interpretation of the part as quickly as possible. If this interpretation is judged unacceptable by a process planner, alternatives can be generated on demand. The feature finder uses a hint-based approach, and combines artificial intelligence techniques, such as blackboard architecture and uncertain reasoning, with the geometric completion procedures first introduced in the OOFF system previously developed at USC.

Integration of feature based design and feature recognition

Interlinking design and process planning plays a key role in realizing Computer Integrated Manufacturing (CIM). Given a part geometry from a CAD system, CAPP generates a sequenced set of instructions to manufacture the specified part. In order to do that, CAPP has to recognize manufacturing features of the part and the relevant information about precision requirements such as surface roughness as well as dimensional and geometric tolerances. Since geometric models from most of the current CAD systems do not incorporate this manufacturing information, human intervention at the first stage of CAPP is inevitable. This has been a major hindrance to information flow between design and process planning. This paper proposes an approach for interlinking CAD and CAPP, and describes the relevant efforts towards it: recognition of machining features, handling of manufacturing information, and implementation …

An approach for interlinking design and process planning

This article presents a system dubbed IF/sup 2/ (Integrated Incremental Feature Finder), which functions as a feature recognizer or a feature model converter depending on whether the input CAD data contains design features. IF/sup 2/ recognizes three types of machining features: holes, slots and pockets. This article discusses recognition algorithms for slots and pockets. Recognition algorithms for holes are similar to those of slots (Han, 1996).

Feature recognition from CAD models

Information security and assurance are new frontiers for collaborative design. In this context, information assurance (IA) refers to methodologies to protect engineering information by ensuring its availability, confidentiality, integrity, non-repudiation, authentication, access control, etc. In collaborative design, IA techniques are needed to protect intellectual property, establish security privileges and create ‘need to know’ protections on critical features. Aside from 3D watermarking, research on how to provide IA to distributed collaborative engineering teams is largely non-existent. This paper provides a framework for IA within collaborative design. It is based on a technique we call role-based viewing, which is achieved through integration of multi-resolution geometry and security models. In this way, 3D models are geometrically partitioned, and the partitioning is used to create multi-resolution mesh hierarchies that …

Role-based viewing envelopes for information protection in collaborative modeling

Current feature research takes two main approaches to feature model generation: feature recognition and feature based design. Feature recognition extracts features from a solid model. The feature based design approach allows designers to use directly a set of predefined primitive features. However, the features used in design are not necessarily manufacturing features, and therefore a conversion process is needed, which transforms the design feature model into a manufacturing feature model. It is called feature model conversion.

3D geometric reasoning algorithms for feature recognition

Solid modelers and other CAD/CAM subsystems are moving to distributed heterogeneous computing environments, so as to support design and manufacturing processes that are temporally and spatially distributed. Communication and collaboration among the software components of such distributed systems require protocols for accessing remote objects. This paper discusses an approach that provides transparent access to diverse solid modelers in a distributed environment. A solid modeler is augmented with a software wrapper, called an adaptor, so as to provide a uniform application programming interface (API). Applications interact with the uniform API and need not concern themselves with the specifics of the modeling systems used. API calls are implemented in a client-server architecture, in which a modeler and its adaptor function as a geometry server, and various applications communicate with the …

Modeler-independent feature recognition in a distributed environment

This paper proposes to integrate feature recognition and process planning in the machining domain. The input part is analyzed to produce a set of setups which might be needed to manufacture the part. Then, a two-layered search strategy is adopted, where a node of the upper layer corresponds to a specific setup, and a node of the lower layer corresponds to a specific process for a feature. For each visited setup node, tool database is consulted in order to generate manufacturable features, feature dependencies are established, and the lower layer search is invoked. The lower layer computes an optimal machining sequence and its manufacturing cost. Then, the control gets returned to the upper layer. Together with the manufacturing cost computed at the lower layer, setup cost analysis guides the upper layer's setup space search. Eventually, a setup sequence is generated where an optimal machining sequence …

STEP-based feature recognition for manufacturing cost optimization

Recent advances in 3D reconstruction and tracking technologies have made it possible to volumetrically capture human body and performance at real time. In the field of human-computer interaction, however, no works have been reported on the user study made with such volumetric capture avatars. This paper investigates how the volumetric capture avatar affects users' sense of social presence in immersive virtual environments. In our experiments, the volumetric capture avatar of an actor is compared with the actor captured in 2D video and another 3D avatar obtained by pre-scanning the actor. The experiment results show that users have the highest sense of social presence with the volumetric capture avatar when performing dynamic tasks whereas they have higher sense of social presence with the volumetric capture avatar and 2D video than with the pre-scanned avatar when performing static tasks. These …

Effects of volumetric capture avatars on social presence in immersive virtual environments

Texture-based methods and connected component (CC) methods have been widely used for text localization. However, these two primary methods have their own strength and weakness. This paper proposes a hybrid approach of the two methods for text localization in complex images. An automatically constructed MLP-based texture classifier can increase the recall rates for complex images with much less user intervention and no explicit feature extraction. The CC-based filtering based on the geometry and shape information enhances the precision rates without affecting overall performance. Then, the time-consuming texture analysis for less relevant pixels is avoided by using CAMShift. Our experimentation shows that the proposed hybrid approach leads to not only robust but also efficient text localization.

Hybrid approach to efficient text extraction in complex color images

This paper presents an overview of hint-based feature recognition algorithms. A hint is a piece of information that implies a feature’s existence. Geometric completion procedures start from the hint instances, perform extensive geometric reasoning and finally construct feature instances. This paper describes the IF 2 , F-Rex and FBMach systems, and shows that the hint-based reasoning can deal with complex feature intersections.

Hint-based reasoning for feature recognition: status report

This paper presents a method for securing collaborative design using multi-level modeling. When a team of designers works collaboratively on a 3D assembly model, a component of the assembly is presented in a full detail to those who have full access privileges to the component, but in an abstract level of detail to those who have less access privileges. Such various levels of detail can be created in two phases: volumetric feature removal which is achieved through interactive feature recognition on the CAD model, and multi-resolution mesh construction which is based on polygonal simplification. Appropriate representations of the assembly are extracted by direction of access matrix, and then presented to the users participating in collaborative design. The key issues in developing the secure collaborative design system are discussed, and the implementation results are reported.

Multi-level modeling and access control for data sharing in collaborative design

In a one-to-many mixed reality collaboration environment, where multiple local users wearing AR headsets are supervised by a remote expert wearing a VR HMD, we evaluated three view-sharing techniques: 2D video, 360 video, and 3D model augmented with 2D video. Through a pilot test, the weaknesses of the techniques were identified, and additional features were integrated into them. Then, their performances were compared in two different collaboration scenarios based on search and assembling. In the first scenario, a local user performed both search and assembling. In the second scenario, two local users had dedicated roles, one for search and the other for assembling. The experiment results showed that the 3D model augmented with 2D video was time-efficient, usable, less demanding and most preferred in one-to-many mixed reality collaborations.

A user study on view-sharing techniques for one-to-many mixed reality collaborations

The reduced gravity experienced in lunar or Martian surfaces can be simulated on the earth using a cable-driven system, where the cable lifts a person to reduce his or her weight. This paper presents a novel cable-driven system designed for the purpose. It is integrated with a head-mounted display and a motion capture system. Focusing on jump motion within the system, this paper proposes to scale the jump and reports the experiments made for quantifying the extent to which a jump can be scaled without the discrepancy between physical and virtual jumps being noticed by the user. With the tolerable range of scaling computed from these experiments, an application named retargeted jump is developed, where a user can jump up onto virtual objects while physically jumping in the real-world flat floor. The core techniques presented in this paper can be extended to develop extreme-sport simulators such as …

Scaled jump in gravity-reduced virtual environments

Recognition of machining features provides a bridge between Computer Aided Design CAD and Computer Aided Manufacturing CAM of machined parts. CAD produces part descriptions in terms of geometric entities or design features, which need not coincide with the manufacturing features needed by process planning activities. The CAD data must therefore be interpreted so as to generate part representations in terms of machining features. When the CAD data contain only nominal geometry information, feature recognition is required. When the CAD data contain design features inserted in a feature based design system, feature model conversion is required. This paper surveys research on feature recognition, feature based design and feature model conversion and raises important issues.

Survey of feature research

Object manipulation techniques in immersive virtual environments are either inaccurate or slow. We present a novel technique, PinNPivot, where pins are used to constrain 1DOF/2DOF/3DOF rotations. It also supports 6DOF manipulation and 3DOF translation. A comparison with three existing techniques shows that PinNPivot is significantly more accurate and faster.

Pinnpivot: Object manipulation using pins in immersive virtual environments

Manufacturing analysis programs that operate in a batch mode are inappropriate for a concurrent engineering environment, in which designers interact with an evolving product model and require rapid feedback on the manufacturing implications of design actions. This paper discusses a design for an automatic recognizer of machining features that operates incrementally, updating its results efficiently after each design step. The Incremental Feature Finder (IFF) builds upon an earlier, batch recognizer called OOFF, developed at USC in the late 1980s. IFF exploits spatial locality and feature dependency information, stored in a Truth Maintenance System, to improve its performance.

Incremental recognition of machining features

Information security and assurance are new frontiers for collaborative design. In this context, information assurance (IA) refers to methodologies to protect engineering information by ensuring its availability, confidentiality, integrity, nonrepudiation, authentication, access control, etc. In collaborative design, IA techniques are needed to protect intellectual property, establish security privileges and create “need to know” protections on critical features. This paper provides a framework for information assurance within collaborative design based on a technique we call Role-Based Viewing . We extend upon prior work to present Hierarchical Role-Based Viewing as a more flexible and practical approach since role hierarchies naturally reflect an organization’s lines of authority and responsibility. We establish a direct correspondence between multilevel security and multiresolution surfaces where a hierarchy is represented …

Hierarchical role-based viewing for multilevel information security in collaborative CAD

Process planning plays a key role by linking CAD and CAM. Its front-end is feature recognition, but feature recognition research has not been in accord with the requirements of process planning. This paper presents an effort for integrating the two activities: feature-based machining sequence generation primarily based on tool capabilities. The system recognizes only manufacturable features by consulting the tool database, and simultaneously constructs dependencies among the features. Then, the algorithm is used to search for an optimal machining sequence by the aid of the feature dependencies and a manufacturing cost function.

Manufacturing feature recognition toward integration with process planning

This paper presents a novel approach to real-time 3D modeling of workspace for manipulative robotic tasks. First, we establish the three fundamental principles that human uses for modeling and interacting with environment. These principles have led to the development of an integrated approach to real-time 3D modeling, as follows: 1) It starts with a rapid but approximate characterization of the geometric configuration of workspace by identifying global plane features. 2) It quickly recognizes known objects in workspace and replaces them by their models in database based on in-situ registration. 3) It models the geometric details on the fly adaptively to the need of the given task based on a multi-resolution octree representation. SIFT features with their 3D position data, referred to here as stereo-sis SIFT, are used extensively, together with point clouds, for fast extraction of global plane features, for fast recognition of …

A real-time 3D workspace modeling with stereo camera

Dimension Expansion for Untangling Mass-Spring System

Visualizing Simulated Airflow and Thermal Comfort in Extended Reality

A user study on air conditioner’s airflow visualization in mobile AR

Interaction With Virtual Objects Using Human Pose and Shape Estimation

Full-Body Interaction in Mixed Reality using 3D Pose and Shape Estimation

A Simple but Effective AR Framework for Human-Object Interaction

Superpixel-guided Sampling for Compact 3D Gaussian Splatting

RoCoTex: A Robust Method for Consistent Texture Synthesis with Diffusion Models

Model-Based Segmentation-Supported Camera Tracking in Fab’s Indoor Environments

Screen-space Streamline Seeding Method for Visualizing Unsteady Flow in Augmented Reality

Momentum-preserving Inversion Alleviation for Elastic Material Simulation

ConvNeXtPose: A Fast Accurate Method for 3D Human Pose Estimation and Its AR Fitness Application in Mobile Devices

Real-time reconstruction of pipes using RGB-D cameras

Inversion Alleviation for Stable Elastic Body Simulation

An Optimization-based SPH Solver for Simulation of Hyperelastic Solids

Fast Stabilization of Inducible Magnet Simulation

Virtual Air Conditioner’s Airflow Simulation and Visualization in AR

Virtual Object Sizes for Efficient and Convenient Mid-air Manipulation

Modeling and Rendering Non-Euclidean Spaces approximated with Concatenated Polytopes

Constrained Projective Dynamics: Real-Time Simulation of Deformable Objects with Energy-Momentum Conservation

PinNPivot: Object Manipulation using Pins in Immersive Virtual Environments

Simulation of Arbitrarily-shaped Magnetic Objects

Collaborative SLAM and AR-guided Navigation for Floor Layout Inspection

SafeXR: Alerting Walking Persons to Obstacles in Mobile XR Environments

Motion Retargetting based on Dilated Convolutions and Skeleton-specific Loss Functions

Effects of Volumetric Capture Avatars on Social Presence in Immersive Virtual Environments

A User Study on View-sharing Techniques for One-to-Many Mixed Reality Collaborations

Obstacle Detection and Alert System for Smartphone AR Users

Point-Cloud Rendering for Video See-Through Augmented Reality

SafeAR: AR Alert System Assisting Obstacle Avoidance for Pedestrians

Effects of Switchable DOF for Mid-Air Manipulation in Immersive Virtual Environments

Visual Manipulation for Underwater Drag Force Perception in Immersive Virtual Environments

Jumping Further: Forward Jumps in a Gravity-Reduced Immersive Virtual Environment

Magnetization Dynamics for Magnetic Object Interactions

Numerical Calculation of Non-uniform Magnetization Using Experimental Magnetic Field Data

Terrain Rendering with Unlimited Detail and Resolution

Real-time Approximation of a Normal Distribution Function for Normal-mapped Surfaces

Flotation Simulation in a Cable-driven Virtual Environment - A Study with Parasailing

StretchArms: Promoting Stretching Exercise with a Smartwatch

Painterly Morphing Effects for Mobile Smart Devices

Effects of Virtual Arm Representations on Interaction in Virtual Environments

Locomotion Control with Inverted Pendulum Model and Hierarchical Low-dimensional Data

Feature-preserving Procedural Texture

Correspondence-based Fluid Control with a Hybrid Particle-Grid Simulation Method

Simulation of Thin Liquid Jets with Threads

Scaled Jump in Gravity-reduced Virtual Environments

Promoting Stretching Activity with Smartwatch - A Pilot Study

Teacher Assessment of Simulation-based Serious Games for Science Education

Interactive Visualization of Magnetic Field for Virtual Science Experiments

Simulation-based Serious Games for Science Education in Elementary and Middle Schools

Muddy Water Animation with Different Details

Multi-resolution Terrain Rendering with GPU Tessellation

Advanced Hybrid Particle-grid Method with Sub-grid Particle Correction

Label Embedded Treemapping: A Label Overlap Prevention Technique for Zoomable Treemaps and a User Interaction Technique

Computer-generated Iron Filing Art

Bulging-free Dual Quaternion Skinning

A Pilot Study of the Intuitiveness of Smartphone Camera Interface for Elderly Users

Porous Deformable Shell Simulation with Surface Water Flow and Saturation

GPU-optimized Indirect Scalar Displacement Mapping

Memory-efficient Real-time Map Building Using Octree of Planes and Points

Feature-preserving Displacement Mapping With Graphics Processing Unit (GPU) Tessellation

Wave Seeds

Image-space Hierarchical Coherence Buffer

Tablorer - An Interactive Tree Visualization System for Tablet PCs

Layered Occlusion Map for Soft Shadow Generation

RFID-Based Digital Board Game Platforms

Convergence Limit in Numerical Modeling of Steady Contraction Viscoelastic Flow and Time-dependent Behavior Near the Limit

Wave Touch: Educational Game on Interactive Tabletop with Water Simulation

Feature-Preserving Deformation of Tessellated Surfaces

3D Displacement Map based on Surface Curvature

A Situation-aware Cross-platform Architecture for Ubiquitous Game

Leaking Fluids

A Multi-player Arcade Video Game Platform with a Wireless Tangible User Interface

Fast Rendering of Large Crowds using GPU

Arcade Video Game Platform built upon Multiple Sensors

Toward Human-like Real-time Manipulation: from Perception to Motion Planning

Fast Collision Detection using the A-buffer

Motion Synthesis with Decoupled Parameterization

Visibility-based Spatial Reasoning for Object Manipulation in Cluttered Environments

미디어 연구실

교수님 소개

한정현

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Dimension Expansion for Untangling Mass-Spring System

Visualizing Simulated Airflow and Thermal Comfort in Extended Reality

A user study on air conditioner’s airflow visualization in mobile AR

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

한정현

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Dimension Expansion for Untangling Mass-Spring System

Visualizing Simulated Airflow and Thermal Comfort in Extended Reality

A user study on air conditioner’s airflow visualization in mobile AR

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집